ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses Authors: Ningyuan He, Ronghong Huang, Qianqian Tang, Hongyu Wang, Xianghang Mi, Shanqing Guo | Published: 2026-01-29 データ毒性攻撃Prompt leakingModel Extraction Attack 2026.01.29 2026.01.31 Literature Database
GShield: Mitigating Poisoning Attacks in Federated Learning Authors: Sameera K. M., Serena Nicolazzo, Antonino Nocera, Vinod P., Rafidha Rehiman K. A | Published: 2025-12-22 データ毒性攻撃Prompt InjectionPoisoning 2025.12.22 2025.12.24 Literature Database
