Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification

Documenti analoghi

• Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning
  di: Nguyen, Tuc, et al.
  Pubblicazione: (2024)
• Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers
  di: Nguyen, Tuc, et al.
  Pubblicazione: (2024)
• ATLAS: Adaptive Test-Time Latent Steering with External Verifiers for Enhancing LLMs Reasoning
  di: Nguyen, Tuc, et al.
  Pubblicazione: (2026)
• NoMatterXAI: Generating "No Matter What" Alterfactual Examples for Explaining Black-Box Text Classification Models
  di: Nguyen, Tuc, et al.
  Pubblicazione: (2024)
• Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification
  di: Alperin, Kenneth, et al.
  Pubblicazione: (2025)