4 papers
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…
Online Influence Campaigns: Strategies and Vulnerabilities
Andreea Musulan, Veronica Xia, Ethan Kosak-Hine +5
In order to combat the creation and spread of harmful content online, this paper defines and contextualizes the concept of inauthentic, societal-scale manipulation by malicious act…
A Simulation System Towards Solving Societal-Scale Manipulation
Maximilian Puelma Touzel, Sneheel Sarangi, Austin Welch +12
The rise of AI-driven manipulation poses significant risks to societal trust and democratic processes. Yet, studying these effects in real-world settings at scale is ethically and…
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…