FlagThis

Abstract

With a profusion of jailbreaks for LLMs now widely known, a growing concern is that nonexpert malicious actors (the average Jane) could elicit actionable responses to malicious requests. In this work, we examine whether this concern is justified. A non-expert malicious actor requires two ingredients for a successful attack: a powerful jailbreak for their target model, acting on an effective malicious query. For the former, we propose a novel attack strategy based on the multi-armed bandit framework. This allows efficient online learning of the optimal jailbreak from a large choice set via noisy exploration on a small number of queries, with subsequent application of the learnt policy on an exploitation set. For the latter, we curate FRANKENSTEINBENCH, a safety benchmark of 11,279 malicious queries drawn from manual curation over 7 existing benchmarks, along with automated enhancement and generation. Each query is categorized as simple or complex by the technical expertise required to craft it. Our findings confirm the concern. Our bandit-based attack achieves success rates as high as 97% on average over 15 SoTA openweight LLMs. Moreover, adding complexity to queries raises the attack success rate by up to 26% on average across models making it an effective, automatable prompting strategy.