DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction

Documenti analoghi

• PuzzleMark: Implicit Jigsaw Learning for Robust Code Dataset Watermarking in Neural Code Completion Models
  di: Huang, Haocheng, et al.
  Pubblicazione: (2026)
• Probing Privacy Leaks in LLM-based Code Generation via Test Generation
  di: Ge, Yifei, et al.
  Pubblicazione: (2026)
• DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
  di: Chen, Yuchen, et al.
  Pubblicazione: (2026)
• Security of Language Models for Code: A Systematic Literature Review
  di: Chen, Yuchen, et al.
  Pubblicazione: (2024)
• Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets
  di: Xiao, Yuan, et al.
  Pubblicazione: (2026)