PPaperPicks

Siyuan Liang

National University of Singapore, School of Computer of Science, Singapore

29 papers at tracked venues · 27 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-6154-0233 ↗Homepage ↗

Venues

ACM MM ×5AAAI ×4CVPR ×4ICCV ×4NeurIPS ×4ICLR ×3ACL ×2EMNLP ×1ICML ×1IJCAI ×1

Frequent coauthors

Jiawei Liang
DBLP profile ↗ORCID search ↗
×3
Tianrui Lou
DBLP profile ↗ORCID search ↗
×2
Ruoyu Chen
DBLP profile ↗ORCID search ↗
×2
Xinwei Liu
DBLP profile ↗ORCID search ↗
×2
Jiangfan Liu
DBLP profile ↗ORCID search ↗
×1
Zheng Zhang
DBLP profile ↗ORCID search ↗
×1
Shuhan Xu
DBLP profile ↗ORCID search ↗
×1
Zhixiang Guo
DBLP profile ↗ORCID search ↗
×1
Yisong Xiao
DBLP profile ↗ORCID search ↗
×1
Xuxu Liu
DBLP profile ↗ORCID search ↗
×1
Zhiyao Ren
DBLP profile ↗ORCID search ↗
×1
Xuan Wang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles
    AAAI 2026 ·
    Jiangfan Liu
    DBLP profile ↗ORCID search ↗
  2. Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees
    ACL 2026 ·
    Zheng Zhang
    DBLP profile ↗ORCID search ↗
  3. SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
    AAAI 2026 ·
    Shuhan Xu
    DBLP profile ↗ORCID search ↗
  4. 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
    ICCV 2025 ·
    Tianrui Lou
    DBLP profile ↗ORCID search ↗
  5. CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks
    ICCV 2025 ·
    Zhixiang Guo
    DBLP profile ↗ORCID search ↗
  6. Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
    NeurIPS 2025 ·
    Yisong Xiao
    DBLP profile ↗ORCID search ↗
  7. ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models
    ACL 2025 ·
    Xuxu Liu
    DBLP profile ↗ORCID search ↗
  8. Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion
    ICCV 2025 ·
    Jiawei Liang
    DBLP profile ↗ORCID search ↗
  9. ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
    ICML 2025 ·
    Zhiyao Ren
    DBLP profile ↗ORCID search ↗
  10. Interpreting Object-level Foundation Models via Visual Precision Search
    CVPR 2025 ·
    Ruoyu Chen
    DBLP profile ↗ORCID search ↗
  11. Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
    NeurIPS 2025 ·
    Xuan Wang
    DBLP profile ↗ORCID search ↗
  12. Manipulating Multimodal Agents via Cross-Modal Prompt Injection
    ACM MM 2025 ·
    Le Wang
    DBLP profile ↗ORCID search ↗
  13. MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving
    ACM MM 2025 ·
    Aishan Liu
    DBLP profile ↗ORCID search ↗
  14. NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
    ICLR 2025 ·
    Zheng Yi Ho
    DBLP profile ↗ORCID search ↗
  15. Physical Adversarial Camouflage Through Gradient Calibration and Regularization
    IJCAI 2025 ·
    Jiawei Liang
    DBLP profile ↗ORCID search ↗
  16. Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
    EMNLP 2025 ·
    Zonghao Ying
    DBLP profile ↗ORCID search ↗
  17. Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
    CVPR 2025 · Siyuan Liang
  18. T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
    NeurIPS 2025 ·
    Jiayang Liu
    DBLP profile ↗ORCID search ↗
  19. Towards a 3D Transfer-Based Black-Box Attack via Critical Feature Guidance
    ICCV 2025 ·
    Shuchao Pang
    DBLP profile ↗ORCID search ↗
  20. BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
    CVPR 2024 · Siyuan Liang
  21. Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
    NeurIPS 2024 ·
    Mingli Zhu
    DBLP profile ↗ORCID search ↗
  22. Does Few-Shot Learning Suffer from Backdoor Attacks?
    AAAI 2024 ·
    Xinwei Liu
    DBLP profile ↗ORCID search ↗
  23. Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
    CVPR 2024 ·
    Tianrui Lou
    DBLP profile ↗ORCID search ↗
  24. LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions
    ACM MM 2024 ·
    Tianyuan Zhang
    DBLP profile ↗ORCID search ↗
  25. Learning to Optimize Permutation Flow Shop Scheduling via Graph-Based Imitation Learning
    AAAI 2024 ·
    Longkang Li
    DBLP profile ↗ORCID search ↗
  26. Less is More: Fewer Interpretable Region via Submodular Subset Selection
    ICLR 2024 ·
    Ruoyu Chen
    DBLP profile ↗ORCID search ↗
  27. Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning
    ACM MM 2024 ·
    Xinwei Liu
    DBLP profile ↗ORCID search ↗
  28. Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
    ICLR 2024 ·
    Jiawei Liang
    DBLP profile ↗ORCID search ↗
  29. Towards Robust Physical-world Backdoor Attacks on Lane Detection
    ACM MM 2024 ·
    Xinwei Zhang
    DBLP profile ↗ORCID search ↗