9 citations · 30 across the 26 of their papers we have counts for
14 papers · 1 filter
Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
Qi Zhou, Tianlin Li, Qing Guo +4
Recent studies have raised significant concerns regarding the vulnerability of Large Vision Language Models (LVLMs) to maliciously injected or perturbed input images, which can mis…
Fairness Testing of Large Language Models in Role-Playing
Xinyue Li, Zhenpeng Chen, Jie M. Zhang +6
Large Language Models (LLMs) have become foundational in modern language-driven software applications, profoundly influencing daily life. A critical technique in leveraging their p…
Speculative Coreset Selection for Task-Specific Fine-tuning
Xiaoyu Zhang, Juan Zhai, Shiqing Ma +4
Task-specific fine-tuning is essential for the deployment of large language models (LLMs), but it requires significant computational resources and time. Existing solutions have pro…
Towards Trustworthy LLMs for Code: A Data-Centric Synergistic Auditing Framework
Chong Wang, Zhenpeng Chen, Tianlin Li +2
LLM-powered coding and development assistants have become prevalent to programmers' workflows. However, concerns about the trustworthiness of LLMs for code persist despite their wi…
Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks
Shide Zhou, Tianlin Li, Kailong Wang +4
Large language models (LLMs) have revolutionized artificial intelligence, but their increasing deployment across critical domains has raised concerns about their abnormal behaviors…
Perception-guided Jailbreak against Text-to-Image Models
Yihao Huang, Le Liang, Tianlin Li +5
In recent years, Text-to-Image (T2I) models have garnered significant attention due to their remarkable advancements. However, security concerns have emerged due to their potential…
NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicing
Shide Zhou, Tianlin Li, Yihao Huang +4
Deep Neural networks (DNNs), extensively applied across diverse disciplines, are characterized by their integrated and monolithic architectures, setting them apart from conventiona…
BadEdit: Backdooring large language models by model editing
Yanzhou Li, Tianlin Li, Kangjie Chen +5
Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applie…
MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented Generation
Guanyu Wang, Yuekang Li, Yi Liu +6
Augmented generation techniques such as Retrieval-Augmented Generation (RAG) and Cache-Augmented Generation (CAG) have revolutionized the field by enhancing large language model (L…
Purifying Large Language Models by Ensembling a Small Language Model
Tianlin Li, Qian Liu, Tianyu Pang +4
The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to d…
Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One
Tianlin Li, Xiaoyu Zhang, Chao Du +5
The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring al…
FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution
Qi Zhou, Dongxia Wang, Tianlin Li +5
Guided image synthesis methods, like SDEdit based on the diffusion model, excel at creating realistic images from user inputs such as stroke paintings. However, existing efforts ma…
Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective
Yihao Huang, Kaiyuan Yu, Qing Guo +5
In recent years, LiDAR-camera fusion models have markedly advanced 3D object detection tasks in autonomous driving. However, their robustness against common weather corruption such…
Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
Chong Wang, Jian Zhang, Yebo Feng +4
Code large language models (LLMs) face limitations in repository-level code generation due to their lack of awareness of repository-level dependencies (e.g., user-defined attribute…