Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation

Documenti analoghi

• Uncovering Gradient Inversion Risks in Practical Language Model Training
  di: Feng, Xinguo, et al.
  Pubblicazione: (2025)
• Token-Modification Adversarial Attacks for Natural Language Processing: A Survey
  di: Roth, Tom, et al.
  Pubblicazione: (2021)
• An Investigation into Misuse of Java Security APIs by Large Language Models
  di: Mousavi, Zahra, et al.
  Pubblicazione: (2024)
• A Constraint-Enforcing Reward for Adversarial Attacks on Text Classifiers
  di: Roth, Tom, et al.
  Pubblicazione: (2024)
• Mitigating Self-Preference by Authorship Obfuscation
  di: Mahbub, Taslim, et al.
  Pubblicazione: (2025)