collaborators

5 papers

cs.CR2025

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…

cs.CR2025

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

Andy Zhou, Kevin Wu, Francesco Pinto +7

As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial. While current red teaming approaches have made strides in assessing LLM vul…

cs.CL2025

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…

cs.SE2024

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

Chengquan Guo, Xun Liu, Chulin Xie +5

With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant ba…

cs.CR2024

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data

Andy Zhou, Xiaojun Xu, Ramesh Raghunathan +4

Graph-based anomaly detection is pivotal in diverse security applications, such as fraud detection in transaction networks and intrusion detection for network traffic. Standard app…