Publications

• “Sparse Adversarial VideoAttacks with Spatial Transformations” In preceeding of The 32nd British Machine Vision Conference (BMVC)
• “3DVerifier: efficient robustness verification for 3D point cloud models” Machine Learning 2022
• “Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning” In preceeding of AAAI 2023
• “Enhancing robustness in video recognition models: Sparse adversarial attacks and beyond” Neural Networks, 2023
• “Reward Certification for Policy Smoothed Reinforcement Learning” In preceeding of AAAI 2024
• “Position: Building Guardrails for Large Language Models Requires Systematic Design” In preceeding of ICML 2024
• “A survey of safety and trustworthiness of large language models through the lens of verification and validation” Artificial Inteligence Review