Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Mario Rodrguez Bjar

Mario Rodrguez Bjar

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2NLP×2

Frequent co-authors

Mario Rodríguez Béjar2×
Jose L. Hernández-Ramos2×
B. Romera-Paredes1×
Francisco J. Cortés-Delgado1×
S. Braghin1×

Research Timeline

2026
FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework

FunFuzz introduces a multi-island evolutionary fuzzing framework that uses LLMs to generate structured inputs, achieving superior compiler coverage and discovering more unique failures compared to existing LLM-driven fuzzers.

ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming

ContextualJailbreak introduces an evolutionary red-teaming strategy that performs automated search over simulated multi-turn primed dialogues, achieving high jailbreak rates across multiple state-of-the-art LLMs.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.CLRecentMay 4, 2026

FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework

Mario Rodríguez Béjar, B. Romera-Paredes, Jose L. Hernández-Ramos

FunFuzz introduces a multi-island evolutionary fuzzing framework that uses LLMs to generate structured inputs, achieving superior compiler coverage and discovering more unique failures compared to exi…

View →
cs.CLcs.CRRecentMay 4, 2026

ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming

Mario Rodríguez Béjar, Francisco J. Cortés-Delgado, S. Braghin, Jose L. Hernández-Ramos

ContextualJailbreak introduces an evolutionary red-teaming strategy that performs automated search over simulated multi-turn primed dialogues, achieving high jailbreak rates across multiple state-of-t…

View →