ML Research Hub
32.6K subscribers
3.41K photos
134 videos
23 files
3.63K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho
Download Telegram
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs

📝 Summary:
EvoSynth is a new framework that autonomously engineers and evolves novel, code-based jailbreak methods for LLMs, moving beyond prompt refinement. It uses self-correction to create diverse and highly successful attacks, achieving 85.5% ASR against robust models.

🔹 Publication Date: Published on Nov 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12710
• PDF: https://arxiv.org/pdf/2511.12710

==================================

For more data science resources:
https://t.iss.one/DataScienceT

#LLMs #JailbreakAttacks #AISecurity #EvolutionaryAlgorithms #AIResearch
1