Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity
It addresses the problem of improving jailbreak attacks for LLMs, offering a new technique that is incremental but with strong specific gains.
This paper investigates the mechanisms behind FlipAttack's jailbreaking effectiveness by analyzing semantic dissimilarity and introduces Alphabet Index Mapping (AIM), a novel adversarial attack that achieves a 94% attack success rate on GPT-4 in experiments.
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many suffer from computational expense, high token usage, or complex decoding schemes. Liu et al. (2024) introduced FlipAttack, a black-box method that achieves high attack success rates (ASR) through simple prompt manipulation. This paper investigates the underlying mechanisms of FlipAttack's effectiveness by analyzing the semantic changes induced by its flipping modes. We hypothesize that semantic dissimilarity between original and manipulated prompts is inversely correlated with ASR. To test this, we examine embedding space visualizations (UMAP, KDE) and cosine similarities for FlipAttack's modes. Furthermore, we introduce a novel adversarial attack, Alphabet Index Mapping (AIM), designed to maximize semantic dissimilarity while maintaining simple decodability. Experiments on GPT-4 using a subset of AdvBench show AIM and its variant AIM+FWO achieve a 94% ASR, outperforming FlipAttack and other methods on this subset. Our findings suggest that while high semantic dissimilarity is crucial, a balance with decoding simplicity is key for successful jailbreaking. This work contributes to a deeper understanding of adversarial prompt mechanics and offers a new, effective jailbreak technique.