ToxSearch: Evolving Prompts for Toxicity Search in Large Language Models
Large Language Models remain vulnerable to adversarial prompts that elicit toxic content even after safety alignment. We present ToxSearch, a black-box evolutionary framework that tests model safety by evolving prompts in a synchronous steady-state loop. The system employs a diverse set of operators, including lexical substitutions, negation, back-translation, paraphrasing, and two semantic crossover operators, while a moderation oracle provides fitness guidance. Operator-level analysis shows heterogeneous behavior: lexical substitutions offer the best yield-variance trade-off, semantic-similarity crossover acts as a precise low-throughput inserter, and global rewrites exhibit high variance with elevated refusal costs. Using elite prompts evolved on LLaMA 3.1 8B, we observe practically meaningful but attenuated cross-model transfer, with toxicity roughly halving on most targets, smaller LLaMA 3.2 variants showing the strongest resistance, and some cross-architecture models retaining higher toxicity. These results suggest that small, controllable perturbations are effective vehicles for systematic red-teaming and that defenses should anticipate cross-model reuse of adversarial prompts rather than focusing only on single-model hardening.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Distributed Quality-Diversity Search for Toxicity in Large Language Models
Large Language Models remain vulnerable to adversarial prompts that elicit harmful responses, and scaling red-teaming to cover a broad range of failure modes is constrained by the cost of text generation and evaluation. …
Text GenerationDiversifying Toxicity Search in Large Language Models Through Speciation
Evolutionary prompt search is a practical black-box approach for red teaming large language models, however existing methods often collapse onto a small family of high-performing prompts, limiting coverage of distinct fa…
Topic coverageRed TeamingFrenchToxicityPrompts: a Large Benchmark for Evaluating and Mitigating Toxicity in French Texts
Large language models (LLMs) are increasingly popular but are also prone to generating bias, toxic or harmful language, which can have detrimental effects on individuals and communities. Although most efforts is put to a…
PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models
Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmark…
BenchmarkingComprehensive Assessment of Toxicity in ChatGPT
Moderating offensive, hateful, and toxic language has always been an important but challenging topic in the domain of safe use in NLP. The emerging large language models (LLMs), such as ChatGPT, can potentially further a…