Plato's Form: Toward Backdoor Defense-as-a-Service for LLMs with Prototype Representations

Documenti analoghi

• Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems
  di: Gao, Jiaxin, et al.
  Pubblicazione: (2025)
• PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs
  di: Gong, Xueluan, et al.
  Pubblicazione: (2024)
• LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge
  di: Li, Songze, et al.
  Pubblicazione: (2025)
• Hidden Data Privacy Breaches in Federated Learning
  di: Gong, Xueluan, et al.
  Pubblicazione: (2024)
• TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
  di: Dai, Yanbo, et al.
  Pubblicazione: (2025)