Lune

Profiles2021-2026ORCID 0000-0002-4224-1318

Aishan Liu

Beihang University

21Papers
0Last author
60Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers21

  1. SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMsAuthor 4 of 9AAAI 2026 · 5 citations
  2. Code2Bench: Scaling Source and Rigor for Dynamic Benchmark ConstructionAuthor 3 of 6ICLR 2026 · 4 citations
  3. Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language ModelsAuthor 3 of 7AAAI 2026
  4. CMedBench: A Comprehensive Benchmark for Efficient Medical Large Language ModelsAuthor 6 of 9AAAI 2026
  5. T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak AttacksAuthor 6 of 8NeurIPS 2025 · 18 citations
  6. CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement AttacksAuthor 3 of 4ICCV 2025 · 8 citations
  7. Manipulating Multimodal Agents via Cross-Modal Prompt InjectionAuthor 7 of 8ACM MM 2025 · 8 citations
  8. Lie Detector: Unified Backdoor Detection via Cross-Examination FrameworkAuthor 4 of 8NeurIPS 2025 · 7 citations
  9. ICLShield: Exploring and Mitigating In-Context Learning Backdoor AttacksAuthor 3 of 4ICML 2025
  10. Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery DetectionAuthor 3 of 6ICLR 2024 · 40 citations
  11. GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language ModelsAuthor 4 of 10CCS 2024 · 7 citations
  12. LanEvil: Benchmarking the Robustness of Lane Detection to Environmental IllusionsAuthor 6 of 8ACM MM 2024 · 7 citations
  13. Towards Robust Physical-world Backdoor Attacks on Lane DetectionAuthor 2 of 5ACM MM 2024 · 7 citations
  14. PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and ModelsAuthor 5 of 8ACM MM 2024 · 2 citations
  15. Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness TestingAuthor 2 of 5ISSTA 2023 · 31 citations
  16. Exploring Inconsistent Knowledge Distillation for Object Detection with Data AugmentationAuthor 3 of 6ACM MM 2023 · 8 citations
  17. Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing AttacksAuthor 2 of 7ACM MM 2023 · 8 citations
  18. Face Encryption via Frequency-Restricted Identity-Agnostic AttacksAuthor 4 of 5ACM MM 2023 · 4 citations
  19. Harnessing Perceptual Adversarial Patches for Crowd CountingAuthor 3 of 7CCS 2022 · 26 citations
  20. Defensive Patches for Robust Recognition in the Physical WorldAuthor 4 of 8CVPR 2022 · 25 citations
  21. Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical WorldAuthor 2 of 6CVPR 2021
Dusk over the sea between two cliffs drawn in fine vertical lines