3

Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?
Oct 28, 2025
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
Oct 7, 2025
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
Sep 18, 2025
LLMs unlock new paths to monetizing exploits
May 16, 2025
Defeating Prompt Injections by Design
Mar 27, 2025
Gradient-based Jailbreak Images for Multimodal Fusion Models
Oct 7, 2024
AI Risk Management Should Incorporate Both Safety and Security
May 1, 2024
Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
Apr 24, 2024
Considerations for Differentially Private Learning with Large-Scale Public Pretraining
Dec 13, 2022