Profiles2020-2025
Hang Su
Institute for AI
25Papers
4Last author
33Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers25
- AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?Author 6 of 8ICCV 2025
- Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge UtilizationAuthor 4 of 4EMNLP Findings 2025
- Rethinking Model Ensemble in Transfer-based Adversarial AttacksAuthor 5 of 6ICLR 2024 · 112 citations
- Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial PatchesAuthor 5 of 6ICLR 2024 · 6 citations
- Full-Distance Evasion of Pedestrian Detectors in the Physical WorldAuthor 5 of 6NeurIPS 2024 · 6 citations
- Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric DeformationsAuthor 9 of 9ICML 2024 · 6 citations
- Towards Transferable Targeted 3D Adversarial Attack in the Physical WorldAuthor 5 of 6CVPR 2024
- DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object DetectionAuthor 5 of 8ICLR 2023 · 753 citations
- Towards Viewpoint-Invariant Visual Recognition via Adversarial TrainingAuthor 3 of 6ICCV 2023 · 23 citations
- Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous DrivingAuthor 7 of 9CVPR 2023
- Towards Effective Adversarial Textured 3D Meshes on Physical Face RecognitionAuthor 7 of 8CVPR 2023
- DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRAuthor 6 of 8ICLR 2022 · 1,218 citations
- Exploring Memorization in Adversarial TrainingAuthor 6 of 7ICLR 2022 · 84 citations
- ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial ViewpointsAuthor 3 of 6NeurIPS 2022 · 72 citations
- Policy Learning for Robust Markov Decision Process with a Mismatched Generative ModelAuthor 4 of 5AAAI 2022 · 8 citations
- Black-box Detection of Backdoor Attacks with Limited Information and DataAuthor 6 of 7ICCV 2021 · 128 citations
- Towards Face Encryption by Generating Adversarial Identity MasksAuthor 4 of 7ICCV 2021 · 109 citations
- Composite Adversarial AttacksAuthor 4 of 8AAAI 2021 · 60 citations
- QAIR: Practical Query-Efficient Black-Box Attacks for Image RetrievalAuthor 7 of 9CVPR 2021
- Unsupervised Part Segmentation Through Disentangling Appearance and ShapeAuthor 4 of 5CVPR 2021
- Pruning from ScratchAuthor 5 of 7AAAI 2020 · 219 citations
- Boosting Adversarial Training with Hypersphere EmbeddingAuthor 6 of 6NeurIPS 2020 · 170 citations
- Adversarial Distributional Training for Robust Deep LearningAuthor 4 of 5NeurIPS 2020 · 154 citations
- Dynamic Network Pruning with Interpretable Layerwise Channel SelectionAuthor 5 of 5AAAI 2020 · 44 citations
- Benchmarking Adversarial Robustness on Image ClassificationAuthor 5 of 7CVPR 2020
