GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking

Computer Science > Cryptography and Security [Submitted on 14 Jun 2026] GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking Aman Anifer, Vignesh Kumar Kembu, Vishnu M, Antonino Nocera, Vinod P., Amal Murali PK, Akshay S Rajan Large Language Models (LLMs) constitute pivotal components within the AI-dominated information technology ecosystem. To mitigate risks associated with harmful or policy-violating outputs, commercial systems employ advanced alignment strategies and multi-layered content moderation mechanisms. Despite these safeguards, recent research has demonstrated that LLMs remain vulnerable to adversarial manipulation, particularly through jailbreaking and prompt injection techniques. In this work, we propose GAS-Leak-LLM a novel jailbreaking attack based on a genetic algorithm that systematically evolves adversarial suffix to bypass safety constraints. Operating in a strict black-box setting, our method requires no access to model parameters or internals, thereby reflecting realistic threat scenarios in deployed systems. Through the iterative application of selection, mutation, and crossover heuristics, the framework systematically explores the discrete prompt space to identify high-fitness adversarial suffixes. Empirical findings reveal critical shortcomings in existing safety enforcement mechanisms and confirm the effectiveness and practical viability of the proposed attack. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2606.15788 [cs.CR]   (or arXiv:2606.15788v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.15788 Focus to learn more Submission history From: Vignesh Kumar Kembu [view email] [v1] Sun, 14 Jun 2026 12:41:21 UTC (685 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)