← authors · overview

• Long-Range Transformers for Dynamic Spatiotemporal Forecasting
  2021 · 78 citations
• Feature Squeezing Mitigates and Detects Carlini/Wagner Adversarial Examples
  2017 · 41 citations
• Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning
  2017 · 39 citations
• General Multi-label Image Classification with Transformers
  2020 · 21 citations
• Measuring Visual Generalization in Continuous Control from Pixels
  2020 · 8 citations
• Towards Automatic Actor-Critic Solutions to Continuous Control
  2021 · 3 citations
• A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets
  2021 · 1 citations
• Launchpad: Learning to Schedule Using Offline and Online RL Methods
  2022 · 1 citations
• STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
  2025
• STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
  2025
• Reward Is Enough: LLMs Are In-Context Reinforcement Learners
  2025
• TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
  2025
• Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation
  2025
• Adversarial-Playground: A Visualization Suite for Adversarial Sample Generation
  2017
• TaeBench: Improving Quality of Toxic Adversarial Examples
  2024