paperJune 2026Unreviewed

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

Abstract

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

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection
AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{anifer2026gasleakllm,
  title = {{GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking}},
  author = {Aman Anifer and Vignesh Kumar Kembu and Vishnu M and Antonino Nocera and Vinod P. and Amal Murali PK and Akshay S Rajan},
  year = {2026},
  month = jun,
  eprint = {2606.15788},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.15788}
}