← authors · overview

• Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning
  2022 · 4 citations
• A Deep Learning-based Fine-grained Hierarchical Learning Approach for Robust Malware Classification
  2020 · 2 citations
• Attacking interpretable NLP systems
  2025
• From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings
  2024