✨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.me/DataScienceT

#LLMs #JailbreakAttacks #AISecurity #EvolutionaryAlgorithms #AIResearch

✨GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

📝 Summary:
GigaEvo is an open-source framework for LLM-guided evolutionary computation, providing modular tools for complex optimization. It enhances reproducibility of AlphaEvolve-inspired methods with detailed implementations, validated on challenging problems like Heilbronn triangle placement.

🔹 Publication Date: Published on Nov 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.17592
• PDF: https://arxiv.org/pdf/2511.17592
• Project Page: https://airi-institute.github.io/gigaevo-cover/
• Github: https://github.com/FusionBrainLab/gigaevo-core

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

For more data science resources:
✓ https://t.me/DataScienceT

#LLM #EvolutionaryAlgorithms #Optimization #OpenSource #AI