Co(ve)rtex: ML Models as storage channels and their (mis-)applications

Documenti analoghi

• Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
  di: Zaree, Pedram, et al.
  Pubblicazione: (2025)
• AttenMIA: LLM Membership Inference Attack through Attention Signals
  di: Zaree, Pedram, et al.
  Pubblicazione: (2026)
• Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
  di: Mamun, Md Abdullah Al, et al.
  Pubblicazione: (2025)
• That Doesn't Go There: Attacks on Shared State in Multi-User Augmented Reality Applications
  di: Slocum, Carter, et al.
  Pubblicazione: (2023)
• Modeling Hierarchical Thinking in Large Reasoning Models
  di: Shahariar, G M, et al.
  Pubblicazione: (2025)