Search Results for author:
Found 76 papers, 32 papers with code
Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings
Federated learning (FL) enables collaborative model training among multiple clients without the need to expose raw data.
Responsible Diffusion Models via Constraining Text Embeddings within Safe Regions
In this paper, we propose a novel self-discovery approach to identifying a semantic direction vector in the embedding space to restrict text embedding within a safe region.
Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models
Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential.
Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area.
Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
Specifically, the embeddings of old tasks shift in the embedding space after learning new tasks, and the classifier becomes biased towards new tasks due to training solely with new data, hindering the balance between old and new knowledge.
RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis
The success of large language models (LLMs) has attracted many individuals to fine-tune them for domain-specific tasks by uploading their data.
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings
Multimodal Large Language Models (MLLMs) have serious security vulnerabilities. While safety alignment using multimodal datasets consisting of text and data of additional modalities can effectively enhance MLLM's security, it is costly to construct these datasets.
Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion Models
At the tool level, we perform a detailed toxicity analysis of NSFW datasets and compare the performance of different NSFW classifiers, offering deeper insights into their performance alongside a compilation of comprehensive evaluation metrics.
CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
We define jailbreak attacks as an optimization problem within the embedding space of masked language models.
Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning
Data heterogeneity and backdoor attacks rank among the most significant challenges facing federated learning (FL).
SVIA: A Street View Image Anonymization Framework for Self-Driving Applications
In recent years, there has been an increasing interest in image anonymization, particularly focusing on the de-identification of faces and individuals.
ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interaction
This enables the synthesis model to directly produce aesthetically pleasing images without any extra computational cost.
Privacy Evaluation Benchmarks for NLP Models
In this paper, we present a privacy attack and defense evaluation benchmark in the field of NLP, which includes the conventional/small models and large language models (LLMs).
FedMCP: Parameter-Efficient Federated Learning with Model-Contrastive Personalization
Specifically, FedMCP adds two lightweight adapter modules, i. e., the global adapter and the private adapter, to the frozen PLMs within clients.
AIR: Analytic Imbalance Rectifier for Continual Learning
To solve this problem, we propose an analytic imbalance rectifier algorithm (AIR), a novel online exemplar-free continual learning method with an analytic (i. e., closed-form) solution for data-imbalanced class-incremental learning (CIL) and generalized CIL scenarios in real-world continual learning.
EIUP: A Training-Free Approach to Erase Non-Compliant Concepts Conditioned on Implicit Unsafe Prompts
Since image generation is conditioned on text, prompt purification serves as a straightforward solution for content safety.
SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
On average, SemiAdv only needs to query a few hundred times to launch an effective attack with more than 90% success rate.
GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
Furthermore, we categorized the gender biases in the "rejected" responses of GenderAlign into 4 principal categories.
ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning
To evaluate the efficacy of our proposed post-tuning approach, we conduct extension training on the Stable Video Diffusion model.
DPSW-Sketch: A Differentially Private Sketch Framework for Frequency Estimation over Sliding Windows (Technical Report)
The sliding window model of computation captures scenarios in which data are continually arriving in the form of a stream, and only the most recent $w$ items are used for analysis.
PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration
The widespread usage of online Large Language Models (LLMs) inference services has raised significant privacy concerns about the potential exposure of private information in user inputs to malicious eavesdroppers.
Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task
One of these scenarios can be formulated as an online continual learning (OCL) problem.
Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
Jailbreaking attacks can enable Large Language Models (LLMs) to bypass the safeguard and generate harmful content.
DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning
The compensation stream is governed by a Dual-Activation Compensation (DAC) module.
GACL: Exemplar-Free Generalized Analytic Continual Learning
The GACL adopts analytic learning (a gradient-free training technique) and delivers an analytical (i. e., closed-form) solution to the GCIL scenario.
F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
In this paper, we propose an exemplar-free approach--Forward-only Online Analytic Learning (F-OAL).
REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning
The DS-BPT pretrains model in streams of both supervised learning and self-supervised contrastive learning (SSCL) for base knowledge extraction.
Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models
Toon shading is a type of non-photorealistic rendering task of animation.
ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference
We propose ConsistentEE, an early exiting method that is consistent in training and inference.
FastBlend: a Powerful Model-Free Toolkit Making Video Stylization Easier
In the interpolation mode, FastBlend surpasses video interpolation and model-based video processing approaches.
Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding
In the experiments, we evaluate KANGAROO over various knowledge-aware and general NLP tasks in both full and few-shot learning settings, outperforming various KEPLM training paradigms performance in closed-domains significantly.
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
A prevailing belief in attack and defense community is that the higher flatness of adversarial examples enables their better cross-model transferability, leading to a growing interest in employing sharpness-aware minimization and its variants.
DualToken-ViT: Position-aware Efficient Vision Transformer with Dual Token Fusion
Position-aware global tokens also contain the position information of the image, which makes our model better for vision tasks.
PAI-Diffusion: Constructing and Serving a Family of Open Chinese Diffusion Models for Text-to-image Synthesis on the Cloud
Text-to-image synthesis for the Chinese language poses unique challenges due to its large vocabulary size, and intricate character relationships.
TransPrompt v2: A Transferable Prompting Framework for Cross-task Text Classification
We propose TransPrompt v2, a novel transferable prompting framework for few-shot learning across similar or distant text classification tasks.
DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis
In recent years, diffusion models have emerged as the most powerful approach in image synthesis.
On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook
Diffusion models and large language models have emerged as leading-edge generative models, revolutionizing various aspects of human life.
UPFL: Unsupervised Personalized Federated Learning towards New Clients
To address this challenge, we extend the adaptive risk minimization technique into the unsupervised personalized federated learning setting and propose our method, FedTTA.
You Can Backdoor Personalized Federated Learning
The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts.
CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation
CMT disentangles the learning of supervised segmentation and unsupervised masked context prediction for effectively learning the very limited labeled points and mass unlabeled points, respectively.
On the Robustness of Split Learning against Adversarial Attacks
Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i. e., sever and clients only hold partial sub-networks and exchange intermediate computations).
Optimal Linear Subspace Search: Learning to Construct Fast and High-Quality Schedulers for Diffusion Models
In this paper, we first provide a detailed theoretical and empirical analysis of the generation process of the diffusion models based on schedulers.
SLPerf: a Unified Framework for Benchmarking Split Learning
Data privacy concerns has made centralized training of data, which is scattered across silos, infeasible, leading to the need for collaborative learning frameworks.
DocAsRef: An Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely
Automated summary quality assessment falls into two categories: reference-based and reference-free.
Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning
Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks.
Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons
The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones.
Transferable Adversarial Examples with Bayes Approach
In this paper, we explore the transferability of adversarial examples via the lens of Bayesian approach.
Understanding Long Programming Languages with Structure-Aware Sparse Attention
With top-$k$ sparse attention, the most crucial attention relation can be obtained with a lower computational cost.
Case-Aware Adversarial Training
Specifically, the intuition stems from the fact that a very limited part of informative samples can contribute to most of model performance.
Backdoor Defense with Machine Unlearning
First, trigger pattern recovery is conducted to extract the trigger patterns infected by the victim model.
Practical and Light-weight Secure Aggregation for Federated Submodel Learning
Existing work fails to provide a loss-less scheme, or has impractical efficiency.
Contrast R-CNN for Continual Learning in Object Detection
In our paper, we propose a new scheme for continual learning of object detection, namely Contrast R-CNN, an approach strikes a balance between retaining the old knowledge and learning the new knowledge.
Privacy Threats Analysis to Secure Federated Learning
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties.
Weakly-Supervised Open-Retrieval Conversational Question Answering
Our method is more flexible as it can handle both span answers and freeform answers.
DSAL: Deeply Supervised Active Learning from Strong and Weak Labelers for Biomedical Image Segmentation
We use the proposed criteria to select samples for strong and weak labelers to produce oracle labels and pseudo labels simultaneously at each active learning iteration in an ensemble learning manner, which can be examined with IoMT Platform.
Towards Scalable and Privacy-Preserving Deep Neural Network via Algorithmic-Cryptographic Co-design
In this paper, we propose SPNN - a Scalable and Privacy-preserving deep Neural Network learning framework, from algorithmic-cryptographic co-perspective.
Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations
More specifically, we propose a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT-based response ranker to rank the PRF-enhanced responses.
Improving Federated Relational Data Modeling via Basis Alignment and Weight Penalty
Federated learning (FL) has attracted increasing attention in recent years.
EasyTransfer -- A Simple and Scalable Deep Transfer Learning Platform for NLP Applications
The literature has witnessed the success of leveraging Pre-trained Language Models (PLMs) and Transfer Learning (TL) algorithms to a wide range of Natural Language Processing (NLP) applications, yet it is not easy to build an easy-to-use and scalable TL toolkit for this purpose.
A Theoretical Perspective on Differentially Private Federated Multi-task Learning
In the era of big data, the need to expand the amount of data through data sharing to improve model performance has become increasingly compelling.
Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy
The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models.
A Comprehensive Analysis of Information Leakage in Deep Transfer Learning
To the best of our knowledge, our study is the first to provide a thorough analysis of the information leakage issues in deep transfer learning methods and provide potential solutions to the issue.
A Hierarchical Deep Convolutional Neural Network and Gated Recurrent Unit Framework for Structural Damage Detection
Specifically, CNN is utilized to model the spatial relations and the short-term temporal dependencies among sensors, while the output features of CNN are fed into the GRU to learn the long-term temporal dependencies jointly.
Open-Retrieval Conversational Question Answering
We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers.
SueNes: A Weakly Supervised Approach to Evaluating Single-Document Summarization via Negative Sampling
Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical similarity which cannot well capture semantics nor linguistic quality and require a reference summary which is costly to obtain.
InfDetect: a Large Scale Graph-based Fraud Detection System for E-Commerce Insurance
The insurance industry has been creating innovative products around the emerging online shopping activities.
IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results.
Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics
Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent.
Attentive History Selection for Conversational Question Answering
First, we propose a positional history answer embedding method to encode conversation history with position information using BERT in a natural way.
TitAnt: Online Real-time Transaction Fraud Detection in Ant Financial
With the explosive growth of e-commerce and the booming of e-payment, detecting online transaction fraud in real time has become increasingly important to Fintech business.
A Deep Framework for Bone Age Assessment based on Finger Joint Localization
In this study, we applied powerful deep neural network and explored a process in the forecast of skeletal bone age with the specifically combine joints images to increase the performance accuracy compared with the whole hand images.
Semi-Supervised Self-Taught Deep Learning for Finger Bones Segmentation
Segmentation stands at the forefront of many high-level vision tasks.
Review Helpfulness Prediction with Embedding-Gated CNN
Product reviews, in the form of texts dominantly, significantly help consumers finalize their purchasing decisions.
Cross-Domain Review Helpfulness Prediction Based on Convolutional Neural Networks with Auxiliary Domain Discriminators
With the growing amount of reviews in e-commerce websites, it is critical to assess the helpfulness of reviews and recommend them accordingly to consumers.
Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge
We present a deep learning framework for computer-aided lung cancer diagnosis.
Aspect Extraction from Product Reviews Using Category Hierarchy Information
Recent work on aspect extraction is leveraging the hierarchical relationship between products and their categories.
