31 citations · 82 across the 31 of their papers we have counts for
8 papers · 1 filter
AI Security Leaderboard: Methodology, Results and Minimal Standard
Jasper Timm, Lukas Struppek, Ziwei Xu +12
The AI Security Leaderboard is an independent benchmark that ranks the safeguards of frontier AI models from least to most secure. It tests models against the FARAI Minimal Stan…
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
Lukas Struppek, Adam Gleave, Kellin Pelrine
As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight mo…
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey +8
As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, be…
Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility
Brendan Murphy, Dillon Bowen, Shahrad Mohammadzadeh +4
AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates t…
The Structural Safety Generalization Problem
Julius Broomfield, Tom Gibbs, Ethan Kosak-Hine +7
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 a…
Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
Tom Gibbs, Ethan Kosak-Hine, George Ingebretsen +6
Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as mo…
Scaling Trends for Data Poisoning in LLMs
Dillon Bowen, Brendan Murphy, Will Cai +3
LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-t…
Exploiting Novel GPT-4 APIs
Kellin Pelrine, Mohammad Taufeeque, Michał Zając +2
Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, rea…