Forging the Unforgeable: On the Feasibility of Counterfeit Watermarks in Backdoor-Based Dataset Ownership Verification

Documenti analoghi

• MambaITD: An Efficient Cross-Modal Mamba Network for Insider Threat Detection
  di: Kong, Kaichuan, et al.
  Pubblicazione: (2025)
• DMFI: A Dual-Modality Log Analysis Framework for Insider Threat Detection with LoRA-Tuned Language Models
  di: Kong, Kaichuan, et al.
  Pubblicazione: (2025)
• Log2Sig: Frequency-Aware Insider Threat Detection via Multivariate Behavioral Signal Decomposition
  di: Kong, Kaichuan, et al.
  Pubblicazione: (2025)
• SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification
  di: Wang, Yingjia, et al.
  Pubblicazione: (2025)
• Wavelet-Aware Anomaly Detection in Multi-Channel User Logs via Deviation Modulation and Resolution-Adaptive Attention
  di: Kong, Kaichuan, et al.
  Pubblicazione: (2026)