Search Results for author:
Found 159 papers, 79 papers with code
EfficientLLM: Efficiency in Large Language Models
Large Language Models (LLMs) have driven significant progress, yet their growing parameter counts and context windows incur prohibitive compute, energy, and monetary costs.
Generative AI for Autonomous Driving: Frontiers and Opportunities
This survey delivers a comprehensive and critical synthesis of the emerging role of GenAI across the autonomous driving stack.
Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
Finally, we train an intermediate energy neural network to approach the target estimation of log-expectation formulation.
Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
This implies a critical flaw of the current training recipe for reasoning LLMs, which does not encourage efficient thinking adequately, leading to the abuse of thinking patterns.
Could AI Trace and Explain the Origins of AI-Generated Images and Text?
AI-generated content is becoming increasingly prevalent in the real world, leading to serious ethical and societal concerns.
Large Reasoning Models in Agent Scenarios: Exploring the Necessity of Reasoning Capabilities
The rise of Large Reasoning Models (LRMs) signifies a paradigm shift toward advanced computational reasoning.
TruthPrInt: Mitigating LVLM Object Hallucination Via Latent Truthful-Guided Pre-Intervention
In this paper, we first conduct an in-depth exploration of LVLM internal states in relation to OH issues and discover that (1) LVLM internal states are high-specificity per-token indicators of hallucination behaviors.
A Survey on Post-training of Large Language Models
The emergence of Large Language Models (LLMs) has fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration.
Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation
Multimodal retrieval-augmented generation (RAG) enhances the visual reasoning capability of vision-language models (VLMs) by dynamically accessing information from external knowledge bases.
End-to-End Deep Learning for Structural Brain Imaging: A Unified Framework
Brain imaging analysis is fundamental in neuroscience, providing valuable insights into brain structure and function.
From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education
Finally, we propose a multi-agent collaborative framework that combines a Time Series Agent for historical analysis and an MLLM Agent for real-time refinement, enhancing error classification and feedback generation.
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
The rapid proliferation of generative audio synthesis and editing technologies has raised significant concerns about copyright infringement, data provenance, and the spread of misinformation through deepfake audio.
CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries
Our evaluation of 16 models reveals significant disparities, with a stronger performance in Western concepts and weaker results in African and Asian contexts.
Political-LLM: Large Language Models in Political Science
In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection.
Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
Current approaches like chain of thought (CoT) reasoning have augmented the cognitive capabilities of large language models (LLMs), yet their adaptation to MLLMs is hindered by heightened risks of hallucination in cross-modality comprehension.
LLaVA-CoT: Let Vision Language Models Reason Step-by-Step
Large language models have demonstrated substantial advancements in reasoning capabilities, particularly through inference-time scaling, as illustrated by models such as OpenAI's o1.
SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding
We present SpecHub, a novel, efficient sampling-verification method for MDSD that improves acceptance rates with only linear computational overhead.
Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination
The rapid progression of multimodal large language models (MLLMs) has demonstrated superior performance on various multimodal benchmarks.
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
Specifically, we formulate the VLM unlearning task via constructing the Fictitious Facial Identity VQA dataset and apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels.
Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?
To address this, we introduce TrustSim, an evaluation dataset covering 10 CSS-related topics, to systematically investigate the reliability of the LLM simulation.
Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces
In the quantized spaces alignment, we leverage vector quantization to align the different state and action spaces of various tasks, facilitating continual training in the same space.
BenTo: Benchmark Task Reduction with In-Context Transferability
Evaluating large language models (LLMs) is costly: it requires the generation and examination of LLM outputs on a large-scale benchmark of various tasks.
FedCAP: Robust Federated Learning via Customized Aggregation and Personalization
The core of FedCAP is a model update calibration mechanism to help a server capture the differences in the direction and magnitude of model updates among clients.
MLP-KAN: Unifying Deep Representation and Function Learning
Recent advancements in both representation learning and function learning have demonstrated substantial promise across diverse domains of artificial intelligence.
Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective
The perturbation analysis of linear solvers applied to systems arising broadly in machine learning settings -- for instance, when using linear regression models -- establishes an important perspective when reframing these analyses through the lens of a data poisoning attack.
Evaluation of OpenAI o1: Opportunities and Challenges of AGI
-Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis.
LLM4Brain: Training a Large Language Model for Brain Video Understanding
Specifically, we employ fine-tuning techniques on an fMRI encoder equipped with adaptors to transform brain responses into latent representations aligned with the video stimuli.
TTT-Unet: Enhancing U-Net with Test-Time Training Layers for Biomedical Image Segmentation
Biomedical image segmentation is crucial for accurately diagnosing and analyzing various diseases.
Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal
Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are usually static.
Biomedical SAM 2: Segment Anything in Biomedical Images and Videos
Medical image segmentation and video object segmentation are essential for diagnosing and analyzing diseases by identifying and measuring biological structures.
Can Large Language Models Automatically Jailbreak GPT-4V?
In our study, we introduce AutoJailbreak, an innovative automatic jailbreak technique inspired by prompt optimization.
Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancement
Despite recent strides made by AI in image processing, the issue of mixed exposure, pivotal in many real-world scenarios like surveillance and photography, remains inadequately addressed.
Bora: Biomedical Generalist Video Generation Model
This paper introduces Bora, the first spatio-temporal diffusion probabilistic model designed for text-guided biomedical video generation.
Self-Cognition in Large Language Models: An Exploratory Study
Additionally, we also explore the utility and trustworthiness of LLM in the self-cognition state, revealing that the self-cognition state enhances some specific tasks such as creative writing and exaggeration.
Rethinking and Defending Protective Perturbation in Personalized Diffusion Models
Existing purification methods attempt to mitigate this issue but often over-purify images, resulting in information loss.
UniGen: A Unified Framework for Textual Dataset Generation Using Large Language Models
Large Language Models (LLMs) such as GPT-4 and Llama3 have significantly impacted various fields by enabling high-quality synthetic data generation and reducing dependence on expensive human-generated datasets.
ViT-1.58b: Mobile Vision Transformers in the 1-bit Era
Vision Transformers (ViTs) have achieved remarkable performance in various image classification tasks by leveraging the attention mechanism to process image patches as tokens.
Quantifying AI Psychology: A Psychometrics Benchmark for Large Language Models
Inspired by psychometrics, this paper presents a framework for investigating psychology in LLMs, including psychological dimension identification, assessment dataset curation, and assessment with results validation.
1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?
This paper introduces a method to enhance the multilingual performance of LLMs by aggregating knowledge from diverse languages.
Jailbreaking Large Language Models Through Alignment Vulnerabilities in Out-of-Distribution Settings
Recently, Large Language Models (LLMs) have garnered significant attention for their exceptional natural language processing capabilities.
GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding
We evaluate the capabilities of current state-of-the-art MLLMs, including Image LLMs and Video LLMs, in understanding various types of GUI content, especially dynamic and sequential content.
HonestLLM: Toward an Honest and Helpful Large Language Model
Subsequently, we present two approaches to augmenting honesty and helpfulness in LLMs: a training-free enhancement and a fine-tuning-based improvement.
In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
Recent works demonstrated that in-context RL could emerge with self-improvement in a trial-and-error manner when treating RL tasks as an across-episodic sequential prediction problem.
Variational Bayes for Federated Continual Learning
Federated continual learning (FCL) has received increasing attention due to its potential in handling real-world streaming data, characterized by evolving data distributions and varying client classes over time.
Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World
In the digital realm, we evaluate our approach using benchmark datasets for TIOD, achieving an Attack Success Rate (ASR) of up to 98. 21%.
CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code
Experiments conducted on a real-world dataset across five programming languages demonstrate the effectiveness of CodeIP in watermarking LLMs for code generation while maintaining the syntactical correctness of code.
Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach
Subsequently, the membership classifier can be effectively employed to deduce the membership status of a given code sample based on the output of a target code completion model.
Optimization-based Prompt Injection Attack to LLM-as-a-Judge
In this work, we propose JudgeDeceiver, an optimization-based prompt injection attack to LLM-as-a-Judge.
Mora: Enabling Generalist Video Generation via A Multi-Agent Framework
Existing open-source methods struggle to achieve comparable performance, often hindered by ineffective agent collaboration and inadequate training data quality.
Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Masking
The rapid expansion of AI in healthcare has led to a surge in medical data generation and storage, boosting medical AI development.
Conditional Score-Based Diffusion Model for Cortical Thickness Trajectory Prediction
Alzheimer's Disease (AD) is a neurodegenerative condition characterized by diverse progression rates among individuals, with changes in cortical thickness (CTh) closely linked to its progression.
Medical Image Synthesis via Fine-Grained Image-Text Alignment and Anatomy-Pathology Prompting
To address these challenges, we propose a novel medical image synthesis model that leverages fine-grained image-text alignment and anatomy-pathology prompts to generate highly detailed and accurate synthetic medical images.
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
Sora is a text-to-video generative AI model, released by OpenAI in February 2024.
GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
We further characterize the game-theoretic properties of LLMs, such as equilibrium and Pareto Efficiency in repeated games.
Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models
We utilize user history as in-context user preferences to address the first challenge.
MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark
Drawing inspiration from the concept of LLM-as-a-Judge within LLMs, this paper introduces a novel benchmark, termed MLLM-as-a-Judge, to assess the ability of MLLMs in assisting judges across diverse modalities, encompassing three distinct tasks: Scoring Evaluation, Pair Comparison, and Batch Ranking.
I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench
Do large language models (LLMs) exhibit any forms of awareness similar to humans?
Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
To mitigate the weaknesses of existing solutions, we propose a novel defense method, Dual Gradient Pruning (DGP), based on gradient pruning, which can improve communication efficiency while preserving the utility and privacy of CL.
The Radiation Oncology NLP Database
ROND is specifically designed to address this gap in the domain of radiation oncology, a field that offers many opportunities for NLP exploration.
LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?
With the rapid development and widespread application of Large Language Models (LLMs), the use of Machine-Generated Text (MGT) has become increasingly common, bringing with it potential risks, especially in terms of quality and integrity in fields like news, education, and science.
Ranked #2 on
Binary text classification
on MixSet (Binary)
TrustLLM: Trustworthiness in Large Language Models
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
Deep Efficient Private Neighbor Generation for Subgraph Federated Learning
Behemoth graphs are often fragmented and separately stored by multiple data owners as distributed subgraphs in many realistic applications.
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
In recent years, multimodal large language models (MLLMs) such as GPT-4V have demonstrated remarkable advancements, excelling in a variety of vision-language tasks.
ClassLIE: Structure- and Illumination-Adaptive Classification for Low-Light Image Enhancement
A class prediction block is then designed to classify the degradation information by calculating the structure similarity scores on the reflectance map and mean square error on the illumination map.
TransMed: Large Language Models Enhance Vision Transformer for Biomedical Image Classification
Our solution secures the 1st place in the MedFMC challenge.
Robust Computer Vision in an Ever-Changing World: A Survey of Techniques for Tackling Distribution Shifts
As a result, it raises concerns about the overall robustness of the machine learning techniques for computer vision applications that are deployed publicly for consumers.
AlignBench: Benchmarking Chinese Alignment of Large Language Models
Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants.
Improving Interpretation Faithfulness for Vision Transformers
However, ViTs suffer from issues with explanation faithfulness, as their focal points are fragile to adversarial attacks and can be easily changed with even slight perturbations on the input image.
ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models
Though diffusion models excel in image generation, their step-by-step denoising leads to slow generation speeds.
Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise
Observing that simply removing the adversarial noise on the training process of the defensive noise can improve the performance of robust unlearnable examples, we identify that solely the surrogate model's robustness contributes to the performance.
MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning
To solve these challenges, we propose MetaCloak, which solves the bi-level poisoning problem with a meta-learning framework with an additional transformation sampling process to craft transferable and robust perturbation.
Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts
This finding indicates potential exploitable security risks in MLLMs; 2) Based on the acquired system prompts, we propose a novel MLLM jailbreaking attack method termed SASP (Self-Adversarial Attack via System Prompt).
Holistic Evaluation of GPT-4V for Biomedical Imaging
GPT-4V represents a breakthrough in artificial general intelligence (AGI) for computer vision, with applications in the biomedical domain.
Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V
In this paper, we critically evaluate the capabilities of the state-of-the-art multimodal large language model, i. e., GPT-4 with Vision (GPT-4V), on Visual Question Answering (VQA) task.
Towards Graph Foundation Models: A Survey and Beyond
Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and several other domains.
MetaAgents: Simulating Interactions of Human Behaviors for LLM-based Task-oriented Coordination via Collaborative Generative Agents
We propose a novel framework that equips collaborative generative agents with human-like reasoning abilities and specialized skills.
Learning Generalizable Agents via Saliency-Guided Features Decorrelation
Our experimental results demonstrate that SGFD can generalize well on a wide range of test environments and significantly outperforms state-of-the-art methods in handling both task-irrelevant variations and task-relevant variations.
FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models
The rampant spread of fake news has adversely affected society, resulting in extensive research on curbing its spread.
MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
However, in scenarios where LLMs serve as intelligent agents, as seen in applications like AutoGPT and MetaGPT, LLMs are expected to engage in intricate decision-making processes that involve deciding whether to employ a tool and selecting the most suitable tool(s) from a collection of available tools to fulfill user requests.
Evaluation of GPT-3 for Anti-Cancer Drug Sensitivity Prediction
In this study, we investigated the potential of GPT-3 for the anti-cancer drug sensitivity prediction task using structured pharmacogenomics data across five tissue types and evaluated its performance with zero-shot prompting and fine-tuning paradigms.
MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation
The Segment Anything Model (SAM), a foundation model for general image segmentation, has demonstrated impressive zero-shot performance across numerous natural image segmentation tasks.
InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4
To achieve this, we first propose several metrics to access the quality of multimodal instruction data.
Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples
In this paper, we first establish a comprehensive, and rigorous point cloud adversarial robustness benchmark to evaluate adversarial robustness, which can provide a detailed understanding of the effects of the defense and attack methods.
Evaluating Large Language Models for Radiology Natural Language Processing
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP).
Instruction Mining: Instruction Data Selection for Tuning Large Language Models
Large language models (LLMs) are initially pretrained for broad capabilities and then finetuned with instruction-following datasets to improve their performance in interacting with humans.
SAMAug: Point Prompt Augmentation for Segment Anything Model
Starting with an initial point prompt, SAM produces an initial mask, which is then fed into our proposed SAMAug to generate augmented point prompts.
TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models
Through the implementation of TrustGPT, this research aims to enhance our understanding of the performance of conversation generation models and promote the development of language models that are more ethical and socially responsible.
Radiology-GPT: A Large Language Model for Radiology
We introduce Radiology-GPT, a large language model for radiology.
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning
However, constrained by the limited quality of the offline dataset, its performance is often sub-optimal.
Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning
Recent works have shown the potential of diffusion models in computer vision and natural language processing.
FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs
This paper introduces FedSecurity, an end-to-end benchmark that serves as a supplementary component of the FedML library for simulating adversarial attacks and corresponding defense mechanisms in Federated Learning (FL).
Decentralized Federated Learning: A Survey and Perspective
Federated learning (FL) has been gaining attention for its ability to share knowledge while maintaining user data, protecting privacy, increasing learning efficiency, and reducing communication overhead.
BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks
Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information.
Ranked #1 on
Text Summarization
on MeQSum
DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
By detecting the watermark from generated images, copyright infringement can be exposed with evidence.
ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter
However, a grand challenge of exploiting LLMs for multimodal learning is the size of pre-trained LLMs which are always with billions of parameters.
Prompt Engineering for Healthcare: Methodologies and Applications
Prompt engineering is a critical technique in the field of natural language processing that involves designing and optimizing the prompts used to input information into models, aiming to enhance their performance on specific tasks.
DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4
The digitization of healthcare has facilitated the sharing and re-using of medical data but has also raised concerns about confidentiality and privacy.
Memory-adaptive Depth-wise Heterogenous Federated Learning
Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data.
A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT
The goal of AIGC is to make the content creation process more efficient and accessible, allowing for the production of high-quality content at a faster pace.
Securing Biomedical Images from Unauthorized Training with Anti-Learning Perturbation
The volume of open-source biomedical data has been essential to the development of various spheres of the healthcare community since more `free' data can provide individual researchers more chances to contribute.
Unlearnable Graph: Protecting Graphs from Unauthorized Exploitation
While the use of graph-structured data in various fields is becoming increasingly popular, it also raises concerns about the potential unauthorized exploitation of personal data for training commercial graph neural network (GNN) models, which can compromise privacy.
AugGPT: Leveraging ChatGPT for Text Data Augmentation
Text data augmentation is an effective strategy for overcoming the challenge of limited sample sizes in many natural language processing (NLP) tasks.
BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT
Recently, ChatGPT has gained significant attention in research due to its ability to interact with humans effectively.
A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT
This study provides a comprehensive review of recent research advancements, challenges, and opportunities for PFMs in text, image, graph, as well as other data modalities.
Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding
All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning.
Tackling Data Heterogeneity in Federated Learning with Class Prototypes
We propose FedNH, a novel method that improves the local models' performance for both personalization and generalization by combining the uniformity and semantics of class prototypes.
SEAT: Stable and Explainable Attention
Results show that SEAT is more stable against different perturbations and randomness while also keeps the explainability of attention, which indicates it is a more faithful explanation.
PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples
In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes.
Transferable Unlearnable Examples
The unlearnable strategies have been introduced to prevent third parties from training on the data without permission.
Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning
Our main idea is to design the multi-action-branch reward estimation and policy-weighted reward aggregation for stabilized training.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+2
RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
For the input-level, we design a new data augmentation technique as Phase MixUp, which highlights task-relevant objects in the interpolations, thus enhancing input-level regularization and class consistency for target models.
BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs
To bridge this gap, we present--to the best of our knowledge--the first comprehensive benchmark for unsupervised outlier node detection on static attributed graphs called BOND, with the following highlights.
Secure Embedding Aggregation for Federated Representation Learning
We consider a federated representation learning framework, where with the assistance of a central server, a group of $N$ distributed clients train collaboratively over their private data, for the representations (or embeddings) of a set of entities (e. g., users in a social network).
End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models
We propose end-to-end multimodal fact-checking and explanation generation, where the input is a claim and a large collection of web sources, including articles, images, videos, and tweets, and the goal is to assess the truthfulness of the claim by retrieving relevant evidence and predicting a truthfulness label (e. g., support, refute or not enough information), and to generate a statement to summarize and explain the reasoning and ruling process.
Data-Free Adversarial Knowledge Distillation for Graph Neural Networks
Graph neural networks (GNNs) have been widely used in modeling graph structured data, owing to its impressive performance in a wide range of practical applications.
PyGOD: A Python Library for Graph Outlier Detection
PyGOD is an open-source Python library for detecting outliers in graph data.
Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation
Furthermore, we propose a Federated learning paradigm with privacy-preserving Relation embedding aggregation (FedR) to tackle the privacy issue in FedE.
FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization
To this end, this paper proposes FedHM, a novel heterogeneous federated model compression framework, distributing the heterogeneous low-rank models to clients and then aggregating them into a full-rank model.
Structure-Preserving Graph Kernel for Brain Network Classification
This paper presents a novel graph-based kernel learning approach for connectome analysis.
Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding
Event extraction is typically modeled as a multi-class classification problem where event types and argument roles are treated as atomic symbols.
DoubleStar: Long-Range Attack Towards Depth Estimation based Obstacle Avoidance in Autonomous Systems
By exploiting the weaknesses of the stereo matching in depth estimation algorithms and the lens flare effect in optical imaging, we propose DoubleStar, a long-range attack that injects fake obstacle depth by projecting pure light from two complementary light sources.
FedDiscrete: A Secure Federated Learning Algorithm Against Weight Poisoning
Federated learning (FL) is a privacy-aware collaborative learning paradigm that allows multiple parties to jointly train a machine learning model without sharing their private data.
Source Inference Attacks in Federated Learning
However, existing MIAs ignore the source of a training member, i. e., the information of which client owns the training member, while it is essential to explore source privacy in FL beyond membership privacy of examples from all clients.
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data
In this work, we observe an interesting phenomenon that the variations of parameters are always AWPs when tuning the trained clean model to inject backdoors.
DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN
In the information explosion era, recommender systems (RSs) are widely studied and applied to discover user-preferred information.
Multiplex Graph Networks for Multimodal Brain Network Analysis
In this paper, we propose MGNet, a simple and effective multiplex graph convolutional network (GCN) model for multimodal brain network analysis.
Joint Embedding of Structural and Functional Brain Networks with Graph Neural Networks for Mental Illness Diagnosis
Multimodal brain networks characterize complex connectivities among different brain regions from both structural and functional aspects and provide a new means for mental disease analysis.
Local-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data
Federated learning enables multiple clients to collaboratively learn a global model by periodically aggregating the clients' models without transferring the local data.
Subgraph Federated Learning with Missing Neighbor Generation
Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions.
Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networks
Based on them, we design MinGE to directly calculate the ideal node embedding dimension for any graph.
Federated Multi-View Learning for Private Medical Data Integration and Analysis
This paper aims to provide a generic Federated Multi-View Learning (FedMV) framework for multi-view data leakage prevention, which is based on different types of local data availability and enables to accommodate two types of problems: Vertical Federated Multi-View Learning (V-FedMV) and Horizontal Federated Multi-View Learning (H-FedMV).
User Preference-aware Fake News Detection
The majority of existing fake news detection algorithms focus on mining news content and/or the surrounding exogenous context for discovering deceptive signals; while the endogenous preference of a user when he/she decides to spread a piece of fake news or not is ignored.
Ranked #1 on
Graph Classification
on UPFD-GOS
Membership Inference Attacks on Knowledge Graphs
Membership inference attacks (MIAs) infer whether a specific data record is used for target model training.
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
FedGraphNN is built on a unified formulation of graph FL and contains a wide range of datasets from different domains, popular GNN models, and FL algorithms, with secure and efficient system support.
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!
Finally, we investigate two defence strategies to protect the victim model and find that unless the performance of the victim model is sacrificed, both model ex-traction and adversarial transferability can effectively compromise the target models
Membership Inference Attacks on Machine Learning: A Survey
In recent years, MIAs have been shown to be effective on various ML models, e. g., classification models and generative models.
FedMood: Federated Learning on Mobile Health Data for Mood Detection
Depression is one of the most common mental illness problems, and the symptoms shown by patients are not consistent, making it difficult to diagnose in the process of clinical practice and pathological research.
EXPLORING VULNERABILITIES OF BERT-BASED APIS
We then demonstrate how the extracted model can be exploited to develop effective attribute inference attack to expose sensitive information of the training data.
Privacy and Robustness in Federated Learning: Attacks and Defenses
Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries.
Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks
Our studies show that mixup is a domain-independent data augmentation technique to pre-trained language models, resulting in significant performance improvement for transformer-based models.
Secure Network Release with Link Privacy
Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).
Federated Model Distillation with Noise-Free Differential Privacy
Conventional federated learning directly averages model weights, which is only possible for collaboration between models with homogeneous architectures.
A Survey on Text Classification: From Shallow to Deep Learning
The last decade has seen a surge of research in this area due to the unprecedented success of deep learning.
LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy
In this paper, we proposed a novel design of local differential privacy mechanism for federated learning to address the abovementioned issues.
Natural Backdoor Attack on Text Data
Recently, advanced NLP models have seen a surge in the usage of various applications.
Secure Deep Graph Generation with Link Differential Privacy
Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).
SplitFed: When Federated Learning Meets Split Learning
SL provides better model privacy than FL due to the machine learning model architecture split between clients and the server.
Differentially Private Deep Learning with Smooth Sensitivity
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT
There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously.
Near-Zero-Cost Differentially Private Deep Learning with Teacher Ensembles
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
Private Deep Learning with Teacher Ensembles
Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information.
Self-Activation Influence Maximization
We incorporate self activation into influence propagation and propose the self-activation independent cascade (SAIC) model: nodes may be self activated besides being selected as seeds, and influence propagates from both selected seeds and self activated nodes.
Social and Information Networks
Adversarial Attack and Defense on Graph Data: A Survey
Therefore, this review is intended to provide an overall landscape of more than 100 papers on adversarial attack and defense strategies for graph data, and establish a unified formulation encompassing most graph adversarial learning models.
Private Model Compression via Knowledge Distillation
To benefit from the on-device deep learning without the capacity and privacy concerns, we design a private model compression framework RONA.
Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks
Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks, where a meta-graph is a composition of meta-paths that captures the complex structural information.
Deep Learning Towards Mobile Applications
In this paper, we provide an overview of the current challenges and representative achievements about pushing deep learning on mobile devices from three aspects: training with mobile data, efficient inference on mobile devices, and applications of mobile deep learning.
Multi-Round Influence Maximization (Extended Version)
In this paper, we study the Multi-Round Influence Maximization (MRIM) problem, where influence propagates in multiple rounds independently from possibly different seed sets, and the goal is to select seeds for each round to maximize the expected number of nodes that are activated in at least one round.
Social and Information Networks
Contaminant Removal for Android Malware Detection Systems
The results indicate that once we remove contaminants from the datasets, we can significantly improve both malware detection rate and detection accuracy
Cryptography and Security
