MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification

Documenti analoghi

• MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
  di: Jiang, Weisen, et al.
  Pubblicazione: (2025)
• SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
  di: Chen, Shuhao, et al.
  Pubblicazione: (2026)
• MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
  di: Ding, Ruyi, et al.
  Pubblicazione: (2025)
• Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
  di: Koga, Tatsuki, et al.
  Pubblicazione: (2024)
• BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts
  di: Wang, Qingyue, et al.
  Pubblicazione: (2025)