7 papers · 1 filter
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Kyle O'Brien, Stephen Casper, Quentin Anthony +7
Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can…
Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
Xander Davies, Eric Winsor, Alexandra Souly +4
LLM developers have imposed technical interventions to prevent fine-tuning misuse attacks, attacks where adversaries evade safeguards by fine-tuning the model using a public API. P…
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…
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…
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…
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…