4 citations · 9 across the 19 of their papers we have counts for
19 papers
Calling the Bluff: Detecting Ever-Shifting Harmful Chat Dialogue via Ordered Reasoning Chain Regularization
Haojie Yu, Ziyou Jiang, Dandan Wang +6
Harmful chat dialogues are ever-shifting through type-shifting and lexical evasion, yet we find they share invariant principles, i.e., an Ordered Reasoning Chain (ORC) of recurring…
From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
Mengzhuo Chen, Junjie Wang, Zhe Liu +3
LLM agents increasingly rely on agent harness: the runtime infrastructure around the base model that defines execution environments, tool interfaces, context, lifecycle orchestrati…
Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems
Mengzhuo Chen, Junjie Wang, Fangwen Mu +4
Failure attribution, i.e., identifying the responsible agent and decisive step of a failure, is particularly challenging in LLM-based multi-agent systems (MAS) due to their natural…
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
Zhiyuan Chang, Mingyang Li, Yuekai Huang +6
Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending agai…
All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
Ziyou Jiang, Mingyang Li, Junjie Wang +5
Harmful memes are ever-shifting in the Internet communities, which are difficult to analyze due to their type-shifting and temporal-evolving nature. Although these memes are shifti…
Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
Wenshuo Wang, Ziyou Jiang, Junjie Wang +6
Internet memes have emerged as a popular multimodal medium, yet they are increasingly weaponized to convey harmful opinions through subtle rhetorical devices like irony and metapho…
VulRTex: A Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report
Ziyou Jiang, Mingyang Li, Guowei Yang +2
Software vulnerabilities exist in open-source software (OSS), and the developers who discover these vulnerabilities may submit issue reports (IRs) to describe their details. Securi…
Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows
Xuyan Ma, Xiaofei Xie, Yawen Wang +4
Agentic workflows built on low-code orchestration platforms enable rapid development of multi-agent systems, but they also introduce new and poorly understood failure modes that hi…
Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
Haowei Wang, Rupeng Zhang, Junjie Wang +4
Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by retrieving relevant documents from external corpora before generating responses. This approach…
AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
Haowei Wang, Junjie Wang, Xiaojun Jia +5
Vision-Language Model (VLM) based Web Agents represent a significant step towards automating complex tasks by simulating human-like interaction with websites. However, their deploy…
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
Zhiyuan Chang, Mingyang Li, Xiaojun Jia +5
Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses. However, the dependence on externa…
Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
Ziyou Jiang, Mingyang Li, Guowei Yang +4
Information theft attacks pose a significant risk to Large Language Model (LLM) tool-learning systems. Adversaries can inject malicious commands through compromised tools, manipula…
What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA
Zhiyuan Chang, Mingyang Li, Xiaojun Jia +5
Incorporating external knowledge has emerged as a promising way to mitigate outdated knowledge and hallucinations in LLM. However, external knowledge is often imperfect, encompassi…
From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
Haowei Wang, Rupeng Zhang, Junjie Wang +4
Tool-calling has changed Large Language Model (LLM) applications by integrating external tools, significantly enhancing their functionality across diverse tasks. However, this inte…
Adversarial Robustness of Open-source Text Classification Models and Fine-Tuning Chains
Hao Qin, Mingyang Li, Junjie Wang +1
Context:With the advancement of artificial intelligence (AI) technology and applications, numerous AI models have been developed, leading to the emergence of open-source model host…
Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement
Zhiyuan Chang, Mingyang Li, Junjie Wang +3
Text-to-Image Diffusion Models (T2I DMs) have garnered significant attention for their ability to generate high-quality images from textual descriptions. However, these models ofte…
A Roadmap for Software Testing in Open Collaborative Development Environments
Qing Wang, Junjie Wang, Mingyang Li +2
Amidst the ever-expanding digital sphere, the evolution of the Internet has not only fostered an atmosphere of information transparency and sharing but has also sparked a revolutio…
VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
Zhiyuan Chang, Mingyang Li, Junjie Wang +2
Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence. The…
Adversarial Testing for Visual Grounding via Image-Aware Property Reduction
Zhiyuan Chang, Mingyang Li, Junjie Wang +4
Due to the advantages of fusing information from various modalities, multimodal learning is gaining increasing attention. Being a fundamental task of multimodal learning, Visual Gr…