6 citations · 6 across the 16 of their papers we have counts for
18 papers
Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks
Alexandra Souly, Kai Fronsdal, Abby D'Cruz +2
This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI systems take unsanctioned actions o…
Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds
Axel Ahlqvist, Richard Guan, Juan-Pablo Rivera +6
A core obstacle to alignment evaluation is evaluation awareness: capable models can tell when they are being tested rather than deployed, weakening the conclusions a safety evaluat…
EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
Xinning Li, Kemunto Ochwang'i, Aryasomayajula Ram Bharadwaj +2
Frontier large language models can often recognize when they are being evaluated, a capability known as evaluation awareness. If models behave differently in evaluations than in de…
Open Technical Problems in Open-Weight AI Model Risk Management
Stephen Casper, Kyle O'Brien, Shayne Longpre +19
Frontier AI models with openly available weights are steadily becoming more powerful and widely adopted. However, compared to proprietary models, open-weight models pose different…
Prefill Awareness in Large Language Models
Andy Wang, Parv Mahajan, David Demitri Africa +3
Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs. If AI models can reco…
Evaluating whether AI models would sabotage AI safety research
Robert Kirk, Alexandra Souly, Kai Fronsdal +2
We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two co…
UK AISI Alignment Evaluation Case-Study
Alexandra Souly, Robert Kirk, Jacob Merizian +2
This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended goals. Specifically, we evaluate…
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…
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…
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…
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…
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…
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…
Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction
Michal Bravansky, Vaclav Kubon, Suhas Hariharan +1
Interpreting data is central to modern research. Large language models (LLMs) show promise in providing such natural language interpretations of data, yet simple feature extraction…
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…
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk +12
Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluat…
Open Problems in Machine Unlearning for AI Safety
Fazl Barez, Tingchen Fu, Ameya Prabhu +16
As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety…