Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack

Documenti analoghi

• Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
  di: Halloran, John T., et al.
  Pubblicazione: (2026)
• Your Agent Can Defend Itself against Backdoor Attacks
  di: Changjiang, Li, et al.
  Pubblicazione: (2025)
• Learning to Defend by Attacking (and Vice-Versa): Transfer of Learning in Cybersecurity Games
  di: Malloy, Tailia, et al.
  Pubblicazione: (2023)
• Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
  di: Cao, Bochuan, et al.
  Pubblicazione: (2023)
• Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
  di: Obioma, Chibueze Peace, et al.
  Pubblicazione: (2025)