Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference

Documenti analoghi

• Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities
  di: Khare, Avishree, et al.
  Pubblicazione: (2023)
• Instruction Following by Principled Boosting Attention of Large Language Models
  di: Guardieiro, Vitoria, et al.
  Pubblicazione: (2025)
• TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
  di: Goel, Aman, et al.
  Pubblicazione: (2025)
• ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
  di: Frikha, Ahmed, et al.
  Pubblicazione: (2024)
• Towards Understanding the Robustness of Sparse Autoencoders
  di: Saiyed, Ahson, et al.
  Pubblicazione: (2026)