FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs

Documenti analoghi

• EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learning
  di: Meerza, Syed Irfan Ali, et al.
  Pubblicazione: (2024)
• Data Reconstruction Attacks and Defenses: A Systematic Evaluation
  di: Liu, Sheng, et al.
  Pubblicazione: (2024)
• ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery
  di: Gong, Zirui, et al.
  Pubblicazione: (2026)
• FedRecAttack: Model Poisoning Attack to Federated Recommendation
  di: Rong, Dazhong, et al.
  Pubblicazione: (2022)
• FedGIG: Graph Inversion from Gradient in Federated Learning
  di: Xiao, Tianzhe, et al.
  Pubblicazione: (2024)