Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations

Documenti analoghi

• Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion
  di: Zhou, Yinghan, et al.
  Pubblicazione: (2025)
• Is Your Writing Being Mimicked by AI? Unveiling Imitation with Invisible Watermarks in Creative Writing
  di: Zhang, Ziwei, et al.
  Pubblicazione: (2025)
• BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
  di: Wu, Zhengxian, et al.
  Pubblicazione: (2025)
• GTSD: Generative Text Steganography Based on Diffusion Model
  di: Wu, Zhengxian, et al.
  Pubblicazione: (2025)
• From Implicit to Explicit: Enhancing Self-Recognition in Large Language Models
  di: Zhou, Yinghan, et al.
  Pubblicazione: (2025)