PPaperPicks

Tianwei Zhang

Nanyang Technological University, School of Computer Science and Engineering, Singapore

49 papers at tracked venues · 36 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-6595-6650 ↗Homepage ↗

Venues

NeurIPS ×9ICLR ×6ICML ×5ACL ×4EMNLP ×4AAAI ×3ICRA ×3ACM MM ×2CVPR ×2ICCV ×2IROS ×2WWW ×2ECCV ×1ECML-PKDD ×1MLSys ×1NAACL ×1SIGKDD ×1

Frequent coauthors

Haozhao Wang
DBLP profile ↗ORCID search ↗
×4
Qingjie Zhang
DBLP profile ↗ORCID search ↗
×3
Runyi Hu
DBLP profile ↗ORCID search ↗
×3
Rongwu Xu
DBLP profile ↗ORCID search ↗
×3
Yutong Wu
DBLP profile ↗ORCID search ↗
×2
Dikai Liu
DBLP profile ↗ORCID search ↗
×2
Hao Wang
DBLP profile ↗ORCID search ↗
×2
Boheng Li
DBLP profile ↗ORCID search ↗
×2
Wen Zheng Terence Ng
DBLP profile ↗ORCID search ↗
×2
Maosen Zhang
DBLP profile ↗ORCID search ↗
×1
Xu Zhang
DBLP profile ↗ORCID search ↗
×1
Jianshuo Dong
DBLP profile ↗ORCID search ↗
×1

Papers

  1. LeakDojo: Decoding the Leakage Threats of RAG Systems
    ACL 2026 ·
    Maosen Zhang
    DBLP profile ↗ORCID search ↗
  2. ShadeEdit: A Utility-Preserving and Defense-Evasive Knowledge Manipulation Attack in Federated LLMs
    AAAI 2026 ·
    Xu Zhang
    DBLP profile ↗ORCID search ↗
  3. A Benchmark for Semantic Sensitive Information in LLMs Outputs
    ICLR 2025 ·
    Qingjie Zhang
    DBLP profile ↗ORCID search ↗
  4. An Engorgio Prompt Makes Large Language Model Babble on
    ICLR 2025 ·
    Jianshuo Dong
    DBLP profile ↗ORCID search ↗
  5. An LLM-Empowered Adaptive Evolutionary Algorithm for Multi-Component Deep Learning Systems
    AAAI 2025 ·
    Haoxiang Tian
    DBLP profile ↗ORCID search ↗
  6. Automated Red Teaming for Text-to-Image Models Through Feedback-Guided Prompt Iteration with Vision-Language Models
    ICCV 2025 ·
    Wei Xu
    DBLP profile ↗ORCID search ↗
  7. BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach
    ICML 2025 ·
    Haozhao Wang
    DBLP profile ↗ORCID search ↗
  8. Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
    ICML 2025 ·
    Yutong Wu
    DBLP profile ↗ORCID search ↗
  9. Detecting Perception-Based Attacks using Visual Odometry: Inconsistency Modeling and Checking on Robotic States
    ICRA 2025 ·
    Yuan Xu
    DBLP profile ↗ORCID search ↗
  10. Disco4D: Disentangled 4D Human Generation and Animation from a Single Image
    CVPR 2025 ·
    Hui En Pang
    DBLP profile ↗ORCID search ↗
  11. Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
    ACL 2025 ·
    Shujian Yang
    DBLP profile ↗ORCID search ↗
  12. GPT-NER: Named Entity Recognition via Large Language Models
    NAACL 2025 ·
    Shuhe Wang
    DBLP profile ↗ORCID search ↗
  13. Mask Image Watermarking
    NeurIPS 2025 ·
    Runyi Hu
    DBLP profile ↗ORCID search ↗
  14. Masked Sensory-Temporal Attention for Sensor Generalization in Quadruped Locomotion
    ICRA 2025 ·
    Dikai Liu
    DBLP profile ↗ORCID search ↗
  15. Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack
    ICCV 2025 ·
    Xingshuo Han
    DBLP profile ↗ORCID search ↗
  16. Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
    WWW 2025 ·
    Hao Wang
    DBLP profile ↗ORCID search ↗
  17. Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving
    MLSys 2025 ·
    Wei Gao
    DBLP profile ↗ORCID search ↗
  18. Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
    NeurIPS 2025 ·
    Chenhang Cui
    DBLP profile ↗ORCID search ↗
  19. SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
    CVPR 2025 ·
    Yue Cao
    DBLP profile ↗ORCID search ↗
  20. Speculating LLMs' Chinese Training Data Pollution from Their Tokens
    EMNLP 2025 ·
    Qingjie Zhang
    DBLP profile ↗ORCID search ↗
  21. TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
    ICML 2025 ·
    Kangjie Chen
    DBLP profile ↗ORCID search ↗
  22. Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
    NeurIPS 2025 ·
    Yukun Chen
    DBLP profile ↗ORCID search ↗
  23. Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
    NeurIPS 2025 ·
    Boheng Li
    DBLP profile ↗ORCID search ↗
  24. Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models
    NeurIPS 2025 ·
    Chunlong Xie
    DBLP profile ↗ORCID search ↗
  25. Understanding the Dark Side of LLMs' Intrinsic Self-Correction
    ACL 2025 ·
    Qingjie Zhang
    DBLP profile ↗ORCID search ↗
  26. Unified Locomotion Transformer with Simultaneous Sim-to-Real Transfer for Quadrupeds
    IROS 2025 ·
    Dikai Liu
    DBLP profile ↗ORCID search ↗
  27. VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
    ICLR 2025 ·
    Runyi Hu
    DBLP profile ↗ORCID search ↗
  28. When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
    EMNLP 2025 ·
    Cheng Wang
    DBLP profile ↗ORCID search ↗
  29. ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
    NeurIPS 2024 ·
    Guanlin Li
    DBLP profile ↗ORCID search ↗
  30. AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA
    ICML 2024 ·
    Weitao Feng
    DBLP profile ↗ORCID search ↗
  31. Backdoor Attacks with Input-Unique Triggers in NLP
    ECML-PKDD 2024 ·
    Xukun Zhou
    DBLP profile ↗ORCID search ↗
  32. BadEdit: Backdooring Large Language Models by Model Editing
    ICLR 2024 ·
    Yanzhou Li
    DBLP profile ↗ORCID search ↗
  33. Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation
    NeurIPS 2024 ·
    Hangcheng Liu
    DBLP profile ↗ORCID search ↗
  34. COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
    NeurIPS 2024 ·
    Ziyuan Zhang
    DBLP profile ↗ORCID search ↗
  35. Course-Correction: Safety Alignment Using Synthetic Preferences
    EMNLP 2024 ·
    Rongwu Xu
    DBLP profile ↗ORCID search ↗
  36. EvilEdit: Backdooring Text-to-Image Diffusion Models in One Second
    ACM MM 2024 ·
    Hao Wang
    DBLP profile ↗ORCID search ↗
  37. FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation
    ICLR 2024 ·
    Haozhao Wang
    DBLP profile ↗ORCID search ↗
  38. FedDSE: Distribution-aware Sub-model Extraction for Federated Learning over Resource-constrained Devices
    WWW 2024 ·
    Haozhao Wang
    DBLP profile ↗ORCID search ↗
  39. FedNLR: Federated Learning with Neuron-wise Learning Rates
    SIGKDD 2024 ·
    Haozhao Wang
    DBLP profile ↗ORCID search ↗
  40. Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners
    ICRA 2024 ·
    Wen Zheng Terence Ng
    DBLP profile ↗ORCID search ↗
  41. Model X-ray: Detecting Backdoored Models via Decision Boundary
    ACM MM 2024 ·
    Yanghao Su
    DBLP profile ↗ORCID search ↗
  42. Off-dynamics Conditional Diffusion Planners
    IROS 2024 ·
    Wen Zheng Terence Ng
    DBLP profile ↗ORCID search ↗
  43. Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation
    ICML 2024 ·
    Boheng Li
    DBLP profile ↗ORCID search ↗
  44. Robust-Wide: Robust Watermarking Against Instruction-Driven Image Editing
    ECCV 2024 ·
    Runyi Hu
    DBLP profile ↗ORCID search ↗
  45. SAME: Sample Reconstruction against Model Extraction Attacks
    AAAI 2024 ·
    Yi Xie
    DBLP profile ↗ORCID search ↗
  46. State Chrono Representation for Enhancing Generalization in Reinforcement Learning
    NeurIPS 2024 ·
    Jianda Chen
    DBLP profile ↗ORCID search ↗
  47. The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
    ACL 2024 ·
    Rongwu Xu
    DBLP profile ↗ORCID search ↗
  48. Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
    EMNLP 2024 ·
    Rongwu Xu
    DBLP profile ↗ORCID search ↗
  49. You Only Query Once: An Efficient Label-Only Membership Inference Attack
    ICLR 2024 ·
    Yutong Wu
    DBLP profile ↗ORCID search ↗