Julius Broomfield — accepted AI-conference papers

2025

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility

Brendan Murphy, Dillon Bowen, Shahrad Mohammadzadeh, Tom Tseng, Julius Broomfield, Adam Gleave +1

EMNLP 2025

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed fine-tuning APIs, can produce helpful-only models with safeguards de

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

The Structural Safety Generalization Problem

Julius Broomfield, Tom Gibbs, George Ingebretsen, Ethan Kosak-Hine, Tia Nasir, Jason Zhang +4

ACL 2025finding

LLM jailbreaks are a widespread safety challenge. Given this problem has not yet been tractable, we suggest targeting a key failure mechanism: the failure of safety to generalize across semantically equivalent inputs. We further focus the target by requiring desirable tractability properties of atta…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗