PPaperPicks

Zhongyun Hua

8 papers at tracked venues · 8 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Debiased Dual-Invariant Defense for Adversarially Robust Person Re-Identification
  2. Multi-View Collaborative Learning Network for Speech Deepfake Detection
  3. Phoneme-Level Feature Discrepancies: A Key to Detecting Sophisticated Speech Deepfakes
  4. Conditional Backdoor Attack via JPEG Compression
  5. DERD: Data-free Adversarial Robustness Distillation through Self-adversarial Teacher Group
  6. Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay
  7. IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
  8. Once-for-all: Efficient Visual Face Privacy Protection via Person-specific Veils