Search Results for author:
Found 47 papers, 31 papers with code
OpticE: A Coherence Theory-Based Model for Link Prediction
During the learning process, the semantics of each entity are embedded by a vector or a point in a feature space.
How to Select Pre-Trained Code Models for Reuse? A Learning Perspective
Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection.
NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors
With the advancement of deep learning, object detectors (ODs) with various architectures have achieved significant success in complex scenarios like autonomous driving.
Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data.
DarkSAM: Fooling Segment Anything Model to Segment Nothing
In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM.
ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification
Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach.
Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning
First, we utilize the vulnerability patches to construct a vulnerability localization task.
Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
Despite the remarkable capabilities demonstrated by Graph Neural Networks (GNNs) in graph-related tasks, recent research has revealed the fairness vulnerabilities in GNNs when facing malicious adversarial attacks.
No Free Lunch Theorem for Privacy-Preserving LLM Inference
Therefore, it is essential to evaluate the balance between the risk of privacy leakage and loss of utility when conducting effective protection mechanisms.
Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study
In particular, we first explore the ways of transforming structured tabular data into sequential text prompts, as to feed them into LLMs and analyze which table content contributes most to the NL2Vis.
Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation
We argue that these factual reasoning-based explanations cannot answer critical what-if questions: What would happen to the GNN's decision if we were to alter the code graph into alternative structures?
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.
Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing
To equip the graph processing with both high accuracy and explainability, we introduce a novel approach that harnesses the power of a large language model (LLM), enhanced by an uncertainty-aware module to provide a confidence score on the generated answer.
Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback
Large Language Models (LLMs) have shown remarkable progress in automated code generation.
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models.
FedRKG: A Privacy-preserving Federated Recommendation Framework via Knowledge Graph Enhancement
Federated Learning (FL) has emerged as a promising approach for preserving data privacy in recommendation systems by training models locally.
Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit
We also benchmark several state-of-the-art neural models for code intelligence, and provide an open-source toolkit tailored for the rapid prototyping of deep-learning-based code intelligence models.
MISA: Unveiling the Vulnerabilities in Split Federated Learning
This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks.
An Extensive Study on Adversarial Attack against Pre-trained Models of Code
Although several approaches have been proposed to generate adversarial examples for PTMC, the effectiveness and efficiency of such approaches, especially on different code intelligence tasks, has not been well understood.
AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning
In this work, we propose AdvCLIP, the first attack framework for generating downstream-agnostic adversarial examples based on cross-modal pre-trained encoders.
Downstream-agnostic Adversarial Examples
AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder.
Why Does Little Robustness Help? Understanding and Improving Adversarial Transferability from Surrogate Training
Building on these insights, we explore the impacts of data augmentation and gradient regularization on transferability and identify that the trade-off generally exists in the various training mechanisms, thus building a comprehensive blueprint for the regulation mechanism behind transferability.
Scalable Optimal Margin Distribution Machine
Optimal margin Distribution Machine (ODM) is a newly proposed statistical learning framework rooting in the novel margin theory, which demonstrates better generalization performance than the traditional large margin based counterparts.
Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
Deep neural networks are proven to be vulnerable to backdoor attacks.
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.
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
In this paper, we propose BadHash, the first generative-based imperceptible backdoor attack against deep hashing, which can effectively generate invisible and input-specific poisoned images with clean label.
VulCNN: An Image-inspired Scalable Vulnerability Detection System
Furthermore, we conduct a case study on more than 25 million lines of code and the result indicates that VulCNN has the ability to detect large-scale vulnerability.
Entity Resolution with Hierarchical Graph Attention Networks
However, there is often interdependence between different pairs of ER decisions, e. g., the entities from the same data source are usually semantically related to each other.
Ranked #1 on
Entity Resolution
on WDC Watches-small
Accelerating Backward Aggregation in GCN Training with Execution Path Preparing on GPUs
In this paper, we first point out that in a GCN training problem with a given training set, the aggregation stages of its backward propagation phase (called as backward aggregations in this paper) can be converted to partially-active graph processing procedures, which conduct computation on only partial vertices of the input graph.
Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer
While deep face recognition (FR) systems have shown amazing performance in identification and verification, they also arouse privacy concerns for their excessive surveillance on users, especially for public face images widely spread on social networks.
What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code
In this paper, we conduct a thorough structural analysis aiming to provide an interpretation of pre-trained language models for source code (e. g., CodeBERT, and GraphCodeBERT) from three distinctive perspectives: (1) attention analysis, (2) probing on the word embedding, and (3) syntax tree induction.
Cross-Language Binary-Source Code Matching with Intermediate Representations
Binary-source code matching plays an important role in many security and software engineering related tasks such as malware detection, reverse engineering and vulnerability assessment.
Clairvoyance: Intelligent Route Planning for Electric Buses Based on Urban Big Data
Nowadays many cities around the world have introduced electric buses to optimize urban traffic and reduce local carbon emissions.
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.
Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations
Then we propose a hierarchical CB (HCB) algorithm to explore users' interest in the hierarchy tree.
Distributed Optimal Margin Distribution Machine
Optimal margin Distribution Machine (ODM), a newly proposed statistical learning framework rooting in the novel margin theory, demonstrates better generalization performance than the traditional large margin based counterparts.
Towards Making Deep Learning-based Vulnerability Detectors Robust
Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention.
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.
Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction
Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated sentiment, and the opinion span explaining the reason for the sentiment.
Sparse online relative similarity learning
This is clearly inefficient for high dimensional tasks due to its high memory and computational complexity.
Significant Inverse Magnetocaloric Effect induced by Quantum Criticality
Strong fluctuations in the low-$T$ quantum critical regime can give rise to a large thermal entropy change and thus significant cooling effect when approaching the QCP.
Strongly Correlated Electrons
$μ$VulDeePecker: A Deep Learning-Based System for Multiclass Vulnerability Detection
Existing vulnerability detection methods based on deep learning can detect the presence of vulnerabilities (i. e., addressing the binary classification or detection problem), but cannot pinpoint types of vulnerabilities (i. e., incapable of addressing multiclass classification).
A Survey on Graph Processing Accelerators: Challenges and Opportunities
Graph is a well known data structure to represent the associated relationships in a variety of applications, e. g., data science and machine learning.
Distributed, Parallel, and Cluster Computing
SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities
Our experiments with 4 software products demonstrate the usefulness of the framework: we detect 15 vulnerabilities that are not reported in the National Vulnerability Database.
VulDeePecker: A Deep Learning-Based System for Vulnerability Detection
Since deep learning is motivated to deal with problems that are very different from the problem of vulnerability detection, we need some guiding principles for applying deep learning to vulnerability detection.
Differentially Private Online Learning for Cloud-Based Video Recommendation with Multimedia Big Data in Social Networks
In addition, none of them has considered both the privacy of users' contexts (e, g., social status, ages and hobbies) and video service vendors' repositories, which are extremely sensitive and of significant commercial value.
Human mobility synthesis using matrix and tensor factorizations
As the tensor model has a strong ability to describe high-dimensional information, we propose an algorithm to predict human mobility in tensors of location context data.
