75 citations · 173 across the 19 of their papers we have counts for
21 papers
MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems
Chejian Xu, Zhaorun Chen, Jingyang Zhang +5
Hierarchical multi-agent systems (MAS) are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and sec…
DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents
Zhaorun Chen, Xun Liu, Haibo Tong +14
AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and fl…
SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring…
Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
Mintong Kang, Zhaorun Chen, Chejian Xu +6
As LLMs become widespread across diverse applications, concerns about the security and safety of LLM interactions have intensified. Numerous guardrail models and benchmarks have be…
From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models
Chejian Xu, Wei Ping, Peng Xu +5
Long-context capabilities are essential for a wide range of applications, including document and video understanding, in-context learning, and inference-time scaling, all of which…
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen +22
Multimodal foundation models (MMFMs) play a crucial role in various applications, including autonomous driving, healthcare, and virtual assistants. However, several studies have re…
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
Lingzhi Yuan, Xinfeng Li, Chejian Xu +6
Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, pa…
AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
Mintong Kang, Chejian Xu, Bo Li
Recent advancements in large audio-language models (LALMs) have enabled speech-based user interactions, significantly enhancing user experience and accelerating the deployment of L…
AdvAgent: Controllable Blackbox Red-teaming on Web Agents
Chejian Xu, Mintong Kang, Jiawei Zhang +5
Foundation model-based agents are increasingly used to automate complex tasks, enhancing efficiency and productivity. However, their access to sensitive resources and autonomous de…
EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
Zeyi Liao, Lingbo Mo, Chejian Xu +6
Generalist web agents have demonstrated remarkable potential in autonomously completing a wide range of tasks on real websites, significantly boosting human productivity. However,…
ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
Peng Xu, Wei Ping, Xianchao Wu +4
In this work, we introduce ChatQA 2, an Llama 3.0-based model with a 128K context window, designed to bridge the gap between open-source LLMs and leading proprietary models (e.g.,…
ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles
Jiawei Zhang, Chejian Xu, Bo Li
We present ChatScene, a Large Language Model (LLM)-based agent that leverages the capabilities of LLMs to generate safety-critical scenarios for autonomous vehicles. Given unstruct…
KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking
Jiawei Zhang, Chejian Xu, Yu Gai +3
This paper introduces KnowHalu, a novel approach for detecting hallucinations in text generated by large language models (LLMs), utilizing step-wise reasoning, multi-formulation qu…
COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks
Zijian Huang, Wenda Chu, Linyi Li +2
Multi-sensor fusion systems (MSFs) play a vital role as the perception module in modern autonomous vehicles (AVs). Therefore, ensuring their robustness against common and realistic…
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei +16
Generative Pre-trained Transformer (GPT) models have exhibited exciting progress in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the…
SemAttack: Natural Textual Attacks via Different Semantic Spaces
Boxin Wang, Chejian Xu, Xiangyu Liu +2
Recent studies show that pre-trained language models (LMs) are vulnerable to textual adversarial attacks. However, existing attack methods either suffer from low attack success rat…
SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles
Chejian Xu, Wenhao Ding, Weijie Lyu +6
As shown by recent studies, machine intelligence-enabled systems are vulnerable to test cases resulting from either adversarial manipulation or natural distribution shifts. This ha…
Copy Motion From One to Another: Fake Motion Video Generation
Zhenguang Liu, Sifan Wu, Chejian Xu +4
One compelling application of artificial intelligence is to generate a video of a target person performing arbitrary desired motion (from a source person). While the state-of-the-a…
COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks
Fan Wu, Linyi Li, Chejian Xu +5
As reinforcement learning (RL) has achieved near human-level performance in a variety of tasks, its robustness has raised great attention. While a vast body of research has explore…
A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective
Wenhao Ding, Chejian Xu, Mansur Arief +3
Autonomous driving systems have witnessed a significant development during the past years thanks to the advance in machine learning-enabled sensing and decision-making algorithms.…
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
Boxin Wang, Chejian Xu, Shuohang Wang +5
Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. Howev…