449 citations · 1.7k across the 108 of their papers we have counts for
14 papers · 1 filter
Controlled Decoding Attacks on Black-Box LLMs
Jesson Wang, Shawn Li, Wei Yang +4
Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely on access to model weights or n…
MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu +3
Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autor…
GEO-Bench: Benchmarking Ranking Manipulation in Generative Engine Optimization
Ojas Nimase, Zhe Chen, Gengpei Qi +2
Large language models (LLMs) increasingly rank products, documents, and recommendations for user queries, which makes manipulating these rankings a growing concern for fairness and…
Agent Audit: A Security Analysis System for LLM Agent Applications
Haiyue Zhang, Yi Nian, Yue Zhao
What should a developer inspect before deploying an LLM agent: the model, the tool code, the deployment configuration, or all three? In practice, many security failures in agent sy…
AEGIS: No Tool Call Left Unchecked -- A Pre-Execution Firewall and Audit Layer for AI Agents
Aojie Yuan, Zhiyuan Su, Yue Zhao
AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks,…
The Autonomy Tax: Defense Training Breaks LLM Agents
Shawn Li, Yue Zhao
Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practit…
Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
Zhisheng Qi, Utkarsh Sahu, Li Ma +9
Retrieval-Augmented Generation (RAG) has become a cornerstone of knowledge-intensive applications, including enterprise chatbots, healthcare assistants, and agentic memory manageme…
"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
Jiate Li, Defu Cao, Li Li +8
Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), an…
Defenses Against Prompt Attacks Learn Surface Heuristics
Shawn Li, Chenxiao Yu, Zhiyu Ni +4
Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intend…
Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
Jinbo Liu, Defu Cao, Yifei Wei +6
Graph topology is a fundamental determinant of memory leakage in multi-agent LLM systems, yet its effects remain poorly quantified. We introduce MAMA (Multi-Agent Memory Attack), a…
Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
Weidi Luo, Tianyu Lu, Qiming Zhang +8
Recent advances in multi-modal large reasoning models (MLRMs) have shown significant ability to interpret complex visual content. While these models enable impressive reasoning cap…
JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
Yi Nian, Shenzhe Zhu, Yuehan Qin +4
Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailb…
Secure On-Device Video OOD Detection Without Backpropagation
Shawn Li, Peilin Cai, Yuxiao Zhou +7
Out-of-Distribution (OOD) detection is critical for ensuring the reliability of machine learning models in safety-critical applications such as autonomous driving and medical diagn…
A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments
Kaixiang Zhao, Lincan Li, Kaize Ding +3
Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data. With the increas…