← authors · overview

• Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings
  2021 · 20 citations
• DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
  2023 · 2 citations
• Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World
  2025
• Fast Adversarial Attacks on Language Models In One GPU Minute
  2024