activity
20242026
most citedPoisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

6 citations · 6 across the 7 of their papers we have counts for

collaborators

15 papers

cs.AI2026

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…

cs.AI2026

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…

cs.CR2026

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

Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure…

cs.LG2026

Boundary Point Jailbreaking of Black-Box LLMs

Xander Davies, Giorgi Giglemiani, Edmund Lau +3

Frontier LLMs are safeguarded against attempts to extract harmful information via adversarial prompts known as "jailbreaks". Recently, defenders have developed classifier-based sys…

cs.SE2025

RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents

Chengquan Guo, Chulin Xie, Yu Yang +6

Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters, enabling dynamic execution, debugging, and inte…

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…