Andy Zou

Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

Safety Pretraining: Toward the Next Generation of Safe AI

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Tamper-Resistant Safeguards for Open-Weight LLMs

Transferable Adversarial Attack on Vision-enabled Large Language Models

Which Network is Trojaned? Increasing Trojan Evasiveness for Model-Level Detectors