← authors · overview

• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
  2016 · 1420 citations
• On the (Statistical) Detection of Adversarial Examples
  2017 · 377 citations
• Adversarial Perturbations Against Deep Neural Networks for Malware Classification
  2016 · 321 citations
• Towards the Science of Security and Privacy in Machine Learning
  2016 · 192 citations
• Practical Black-Box Attacks against Machine Learning
  2016 · 101 citations
• The Limitations of Deep Learning in Adversarial Settings
  2015 · 72 citations
• On the Effectiveness of Defensive Distillation
  2016 · 58 citations
• A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
  2024 · 17 citations
• Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
  2015 · 8 citations
• Generating Practical Adversarial Network Traffic Flows Using NIDSGAN
  2022 · 6 citations
• The Efficacy of Transformer-based Adversarial Attacks in Security Domains
  2023 · 5 citations
• Adversarial Examples in Constrained Domains
  2020 · 4 citations
• The Space of Adversarial Strategies
  2022 · 3 citations
• Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
  2025 · 1 citations
• Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
  2025