most citedPoisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

6 citations · 6 across the 5 of their papers we have counts for

collaborators

10 papers

cs.LG20256 cited

Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

Alexandra Souly, Javier Rando, Ed Chapman +10

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoni…

cs.AI2025

Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition

Andy Zou, Maxwell Lin, Eliot Jones +14

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these sys…

cs.CL2025

STACK: Adversarial Attacks on LLM Safeguard Pipelines

Ian R. McKenzie, Oskar J. Hollinsworth, Tom Tseng +5

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic and OpenAI guard their latest Opus 4 model and GPT-5 mode…

cs.LG2025

Existing Large Language Model Unlearning Evaluations Are Inconclusive

Zhili Feng, Yixuan Even Xu, Alexander Robey +5

Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed kn…

cs.LG2025

An Example Safety Case for Safeguards Against Misuse

Joshua Clymer, Jonah Weinbaum, Robert Kirk +3

Existing evaluations of AI misuse safeguards provide a patchwork of evidence that is often difficult to connect to real-world decisions. To bridge this gap, we describe an end-to-e…

cs.LG2025

Reward Model Overoptimisation in Iterated RLHF

Lorenz Wolf, Robert Kirk, Mirco Musolesi

Reinforcement learning from human feedback (RLHF) is a widely used method for aligning large language models with human preferences. However, RLHF often suffers from reward model o…