Zifan Wang

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

arXiv 2026

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

arXiv 2025

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

arXiv 2024

Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

arXiv 2024

Arm-Constrained Curriculum Learning for Loco-Manipulation of the Wheel-Legged Robot

arXiv 2024

Universal and Transferable Adversarial Attacks on Aligned Language Models

arXiv 2023

Representation Engineering: A Top-Down Approach to AI Transparency

arXiv 2023

Can LLMs Follow Simple Rules?

arXiv 2023

Unlocking Deterministic Robustness Certification on ImageNet

unlocking-deterministic-robustness

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

arXiv 2019

Andy Zou

founder

Matt Fredrikson

Dan Hendrycks

director

J. Zico Kolter

Long Phan

researcher

Mantas Mazeika

researcher

Nathaniel Li

grad-student

Norman Mu

Sarah Chen

Sean Hendryx