← authors · overview

• Adversarial Unlearning Of Backdoors Via Implicit Hypergradient
  2021 · 37 citations
• DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation
  2020 · 25 citations
• Mitigating Advanced Adversarial Attacks with More Advanced Gradient Obfuscation Techniques
  2020 · 14 citations
• TEST: an End-to-End Network Traffic Examination and Identification Framework Based on Spatio-Temporal Features Extraction
  2019 · 9 citations
• Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information
  2022 · 7 citations
• ASSET: Robust Backdoor Data Detection Across A Multiplicity Of Deep Learning Paradigms
  2023 · 6 citations
• A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks
  2020 · 4 citations
• Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models