May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks

Documenti analoghi

• Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface
  di: Labunets, Andrey, et al.
  Pubblicazione: (2025)
• Systems Security Foundations for Agentic Computing
  di: Christodorescu, Mihai, et al.
  Pubblicazione: (2025)
• Agent Security is a Systems Problem
  di: Christodorescu, Mihai, et al.
  Pubblicazione: (2026)
• Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
  di: Zhan, Qiusi, et al.
  Pubblicazione: (2025)
• Defense Against Prompt Injection Attack by Leveraging Attack Techniques
  di: Chen, Yulin, et al.
  Pubblicazione: (2024)