Yinpeng Dong

Benchmarking Trustworthiness in Multimodal LLMs for Video Understanding AAAI 2026 Any2Critical: Safety-Critical Scenario Generation from Arbitrary Real-World Driving Contexts AAAI 2026 Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability NAACL 2025 Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization EMNLP 2025 STAIR: Improving Safety Alignment with Introspective Reasoning ICML 2025 Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space ACL 2025 AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations? ICCV 2025 Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation ICCV 2025 AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs NAACL 2025 Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models ECCV 2024 MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models NIPS 2024 Diffusion Models are Certifiably Robust Classifiers NIPS 2024 T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models NIPS 2024 Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective NIPS 2024 Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy NIPS 2024 Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning ICML 2024 Robust Classification via a Single Diffusion Model ICML 2024 Rethinking Model Ensemble in Transfer-based Adversarial Attacks ICLR 2024 Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches ICLR 2024 Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training CVPR 2024 Towards Transferable Targeted 3D Adversarial Attack in the Physical World CVPR 2024 Exploring the Transferability of Visual Prompting for Multimodal Large Language Models CVPR 2024 DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks ECCV 2024 Toward Availability Attacks in 3D Point Clouds ICML 2024 Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior ICML 2024 Understanding the Robustness of 3D Object Detection With Bird's-Eye-View Representations in Autonomous Driving CVPR 2023 Towards Viewpoint-Invariant Visual Recognition via Adversarial Training ICCV 2023 Learning Sample Difficulty from Pre-trained Models for Reliable Prediction NIPS 2023 GNOT: A General Neural Operator Transformer for Operator Learning ICML 2023 Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition CVPR 2023 Compacting Binary Neural Networks by Sparse Kernel Selection CVPR 2023 Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos ICCV 2023 Benchmarking Robustness of 3D Object Detection to Common Corruptions CVPR 2023 Isometric 3D Adversarial Examples in the Physical World NIPS 2022 Pre-trained Adversarial Perturbations NIPS 2022 ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints NIPS 2022 Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022 Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks ECCV 2022 Exploring Memorization in Adversarial Training ICLR 2022 GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing ICML 2022 Improving Transferability of Adversarial Patches on Face Recognition With Generative Models CVPR 2021 Bag of Tricks for Adversarial Training ICLR 2021 Accumulative Poisoning Attacks on Real-time Data NIPS 2021 Towards Face Encryption by Generating Adversarial Identity Masks ICCV 2021 Black-Box Detection of Backdoor Attacks With Limited Information and Data ICCV 2021 Boosting Adversarial Training with Hypersphere Embedding NIPS 2020 Adversarial Distributional Training for Robust Deep Learning NIPS 2020 Benchmarking Adversarial Robustness on Image Classification CVPR 2020 Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness ICLR 2020 Understanding and Exploring the Network with Stochastic Architectures NIPS 2020 Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition CVPR 2019 Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks CVPR 2019 Composite Binary Decomposition Networks AAAI 2019 Improving Black-box Adversarial Attacks with a Transfer-based Prior NIPS 2019 Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser CVPR 2018 Towards Robust Detection of Adversarial Examples NIPS 2018 Boosting Adversarial Attacks With Momentum CVPR 2018 Learning Visual Knowledge Memory Networks for Visual Question Answering CVPR 2018 Improving Interpretability of Deep Neural Networks With Semantic Information CVPR 2017 Forecast the Plausible Paths in Crowd Scenes IJCAI 2017 Crowd Scene Understanding with Coherent Recurrent Neural Networks IJCAI 2016