2 papers
cs.CR2026
FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework
Mario RodrÃguez Béjar, B. Romera-Paredes, Jose L. Hernández-Ramos
Modern fuzzers increasingly use Large Language Models (LLMs) to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initialization and sampling variance, whic…
cs.CL2026
ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming
Mario RodrÃguez Béjar, Francisco J. Cortés-Delgado, S. Braghin +1
Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety alignment and elicit harmful responses. A growing body of work shows that contextual priming,…