6 citations · 17 across the 19 of their papers we have counts for
21 papers
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
Yuxi Li, Zhibo Zhang, Kailong Wang +3
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or t…
A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation
Shide Zhou, Kailong Wang, Ling Shi +1
Defining the reasoning boundaries and ensuring the reliability of Large Reasoning Models (LRMs) remains a critical challenge. Current benchmarks primarily rely on static datasets s…
Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving
Xinyi Zheng, Ningke Li, Xiaokun Luan +4
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, leading to their adoption in high-stakes domains such as healthcare, law, and scientific research.…
Boosting Pointer Analysis With LLM-Enhanced Allocation Function Detection
Baijun Cheng, Kailong Wang, Ling Shi +5
Pointer analysis is foundational for many static analysis tasks, yet its effectiveness is often hindered by imprecise modeling of heap allocations, particularly in C/C++ programs w…
Enhancing Semantic Understanding in Pointer Analysis using Large Language Models
Baijun Cheng, Kailong Wang, Ling Shi +4
Pointer analysis has been studied for over four decades. However, existing frameworks continue to suffer from the propagation of incorrect facts. A major limitation stems from thei…
Measuring and Explaining the Effects of Android App Transformations in Online Malware Detection
Guozhu Meng, Zhixiu Guo, Xiaodong Zhang +3
It is well known that antivirus engines are vulnerable to evasion techniques (e.g., obfuscation) that transform malware into its variants. However, it cannot be necessarily attribu…
Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation
Zhibo Zhang, Yuxi Li, Kailong Wang +3
Large Language Models (LLMs) have achieved remarkable success across domains such as healthcare, education, and cybersecurity. However, this openness also introduces significant se…
Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics
Shide Zhou, Kailong Wang, Ling Shi +1
The widespread adoption of Large Language Models (LLMs) in critical applications has introduced severe reliability and security risks, as LLMs remain vulnerable to notorious threat…
Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning
Ningke Li, Yahui Song, Kailong Wang +4
Large language models (LLMs) face the challenge of hallucinations -- outputs that seem coherent but are actually incorrect. A particularly damaging type is fact-conflicting halluci…
Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
Yuxi Li, Zhibo Zhang, Kailong Wang +2
Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly ja…
Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models
Fan Yang, Yihao Huang, Kailong Wang +4
Vision-language pre-training (VLP) models, trained on large-scale image-text pairs, have become widely used across a variety of downstream vision-and-language (V+L) tasks. This wid…
GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models
Zhibo Zhang, Wuxia Bai, Yuxi Li +6
Large language models (LLMs) have achieved unprecedented success in the field of natural language processing. However, the black-box nature of their internal mechanisms has brought…
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…
Semantic-Enhanced Indirect Call Analysis with Large Language Models
Baijun Cheng, Cen Zhang, Kailong Wang +6
In contemporary software development, the widespread use of indirect calls to achieve dynamic features poses challenges in constructing precise control flow graphs (CFGs), which fu…
SPOLRE: Semantic Preserving Object Layout Reconstruction for Image Captioning System Testing
Yi Liu, Guanyu Wang, Xinyi Zheng +4
Image captioning (IC) systems, such as Microsoft Azure Cognitive Service, translate image content into descriptive language but can generate inaccuracies leading to misinterpretati…
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…
Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models
Ningke Li, Yuekang Li, Yi Liu +3
Large language models (LLMs) have transformed the landscape of language processing, yet struggle with significant challenges in terms of security, privacy, and the generation of se…
Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection
Yuxi Li, Yi Liu, Gelei Deng +7
With the expanding application of Large Language Models (LLMs) in various domains, it becomes imperative to comprehensively investigate their unforeseen behaviors and consequent ou…
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…
MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis
Shenao Wang, Yuekang Li, Kailong Wang +4
The advent of MiniApps, operating within larger SuperApps, has revolutionized user experiences by offering a wide range of services without the need for individual app downloads. H…
Digger: Detecting Copyright Content Mis-usage in Large Language Model Training
Haodong Li, Gelei Deng, Yi Liu +7
Pre-training, which utilizes extensive and varied datasets, is a critical factor in the success of Large Language Models (LLMs) across numerous applications. However, the detailed…