Mario Rodríguez Béjar
2 papers · Latest:
Cryptography & Security
FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework
FunFuzz is an LLM-powered evolutionary fuzzer that uses a multi-island approach to enhance exploration, achieving superior compiler coverage and unique failures.
2605.02789
Natural Language ProcessingContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming
ContextualJailbreak uses evolutionary search and multi-turn priming to red-team LLMs, achieving high attack success rates and revealing alignment gaps.
2605.02647
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.