180 citations · 951 across the 62 of their papers we have counts for
63 papers
Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis
Xiyue Zhang, Xiaoyong Xue, Xiaoning Du +3
Federated learning (FL), as a powerful learning paradigm, trains a shared model by aggregating model updates from distributed clients. However, the decoupling of model learning fro…
Large Language Model Supply Chain: Open Problems From the Security Perspective
Qiang Hu, Xiaofei Xie, Sen Chen +1
Large Language Model (LLM) is changing the software development paradigm and has gained huge attention from both academia and industry. Researchers and developers collaboratively e…
MORTAR: A Model-based Runtime Action Repair Framework for AI-enabled Cyber-Physical Systems
Renzhi Wang, Zhehua Zhou, Jiayang Song +3
Cyber-Physical Systems (CPSs) are increasingly prevalent across various industrial and daily-life domains, with applications ranging from robotic operations to autonomous driving.…
Evaluation and Improvement of Fault Detection for Large Language Models
Qiang Hu, Jin Wen, Maxime Cordy +4
Large language models (LLMs) have recently achieved significant success across various application domains, garnering substantial attention from different communities. Unfortunatel…
GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis
Yuqiang Sun, Daoyuan Wu, Yue Xue +5
Smart contracts are prone to various vulnerabilities, leading to substantial financial losses over time. Current analysis tools mainly target vulnerabilities with fixed control or…
Evaluating the Robustness of Test Selection Methods for Deep Neural Networks
Qiang Hu, Yuejun Guo, Xiaofei Xie +4
Testing deep learning-based systems is crucial but challenging due to the required time and labor for labeling collected raw data. To alleviate the labeling effort, multiple test s…
BehAVExplor: Behavior Diversity Guided Testing for Autonomous Driving Systems
Mingfei Cheng, Yuan Zhou, Xiaofei Xie
Testing Autonomous Driving Systems (ADSs) is a critical task for ensuring the reliability and safety of autonomous vehicles. Existing methods mainly focus on searching for safety v…
How Effective Are They? Exploring Large Language Model Based Fuzz Driver Generation
Cen Zhang, Yaowen Zheng, Mingqiang Bai +6
LLM-based (Large Language Model) fuzz driver generation is a promising research area. Unlike traditional program analysis-based method, this text-based approach is more general and…
Multi-target Backdoor Attacks for Code Pre-trained Models
Yanzhou Li, Shangqing Liu, Kangjie Chen +3
Backdoor attacks for neural code models have gained considerable attention due to the advancement of code intelligence. However, most existing works insert triggers into task-speci…
Active Code Learning: Benchmarking Sample-Efficient Training of Code Models
Qiang Hu, Yuejun Guo, Xiaofei Xie +4
The costly human effort required to prepare the training data of machine learning (ML) models hinders their practical development and usage in software engineering (ML4Code), espec…
A Black-Box Attack on Code Models via Representation Nearest Neighbor Search
Jie Zhang, Wei Ma, Qiang Hu +4
Existing methods for generating adversarial code examples face several challenges: limted availability of substitute variables, high verification costs for these substitutes, and t…
Evading DeepFake Detectors via Adversarial Statistical Consistency
Yang Hou, Qing Guo, Yihao Huang +3
In recent years, as various realistic face forgery techniques known as DeepFake improves by leaps and bounds,more and more DeepFake detection techniques have been proposed. These m…
Evaluating AIGC Detectors on Code Content
Jian Wang, Shangqing Liu, Xiaofei Xie +1
Artificial Intelligence Generated Content (AIGC) has garnered considerable attention for its impressive performance, with ChatGPT emerging as a leading AIGC model that produces hig…
Neural Episodic Control with State Abstraction
Zhuo Li, Derui Zhu, Yujing Hu +6
Existing Deep Reinforcement Learning (DRL) algorithms suffer from sample inefficiency. Generally, episodic control-based approaches are solutions that leverage highly-rewarded past…
ContraBERT: Enhancing Code Pre-trained Models via Contrastive Learning
Shangqing Liu, Bozhi Wu, Xiaofei Xie +2
Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code represen…
Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities
Wei Ma, Shangqing Liu, Mengjie Zhao +5
Past research has examined how well these models grasp code syntax, yet their understanding of code semantics still needs to be explored. We extensively analyze seven code models t…
TransRepair: Context-aware Program Repair for Compilation Errors
Xueyang Li, Shangqing Liu, Ruitao Feng +4
Automatically fixing compilation errors can greatly raise the productivity of software development, by guiding the novice or AI programmers to write and debug code. Recently, learn…
Decompiling x86 Deep Neural Network Executables
Zhibo Liu, Yuanyuan Yuan, Shuai Wang +2
Due to their widespread use on heterogeneous hardware devices, deep learning (DL) models are compiled into executables by DL compilers to fully leverage low-level hardware primitiv…
Towards Understanding the Faults of JavaScript-Based Deep Learning Systems
Lili Quan, Qianyu Guo, Xiaofei Xie +3
Quality assurance is of great importance for deep learning (DL) systems, especially when they are applied in safety-critical applications. While quality issues of native DL applica…
Enhancing Security Patch Identification by Capturing Structures in Commits
Bozhi Wu, Shangqing Liu, Ruitao Feng +3
With the rapid increasing number of open source software (OSS), the majority of the software vulnerabilities in the open source components are fixed silently, which leads to the de…
Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation
Qiang Hu, Yuejun Guo, Xiaofei Xie +4
Deep learning (DL) plays a more and more important role in our daily life due to its competitive performance in industrial application domains. As the core of DL-enabled systems, d…
CodeS: Towards Code Model Generalization Under Distribution Shift
Qiang Hu, Yuejun Guo, Xiaofei Xie +4
Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation. Although DL has been becoming…
Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment
Qiang Hu, Yuejun Guo, Maxime Cordy +4
Deep Neural Networks (DNNs) have gained considerable attention in the past decades due to their astounding performance in different applications, such as natural language modeling,…
LaF: Labeling-Free Model Selection for Automated Deep Neural Network Reusing
Qiang Hu, Yuejun Guo, Maxime Cordy +3
Applying deep learning to science is a new trend in recent years which leads DL engineering to become an important problem. Although training data preparation, model architecture d…