Lignende værker

• Co(ve)rtex: ML Models as storage channels and their (mis-)applications
  af: Mamun, Md Abdullah Al, et al.
  Udgivet: (2023)
• AttenMIA: LLM Membership Inference Attack through Attention Signals
  af: Zaree, Pedram, et al.
  Udgivet: (2026)
• Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
  af: Mamun, Md Abdullah Al, et al.
  Udgivet: (2025)
• Bypassing Prompt Injection Detectors through Evasive Injections
  af: Rahman, Md Jahedur, et al.
  Udgivet: (2026)
• That Doesn't Go There: Attacks on Shared State in Multi-User Augmented Reality Applications
  af: Slocum, Carter, et al.
  Udgivet: (2023)