PPaperPicks

Chaowei Xiao

42 papers at tracked venues · 28 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ICLR ×12NAACL ×8ACL ×6NeurIPS ×5ECCV ×4ICML ×3ICRA ×2AAAI ×1CVPR ×1

Frequent coauthors

Xiaogeng Liu
DBLP profile ↗ORCID search ↗
×2
Yingzi Ma
DBLP profile ↗ORCID search ↗
×2
Peiran Wang
DBLP profile ↗ORCID search ↗
×2
Hao Li
DBLP profile ↗ORCID search ↗
×2
Yue Huang
DBLP profile ↗ORCID search ↗
×2
Qin Liu
DBLP profile ↗ORCID search ↗
×2
Jiongxiao Wang
DBLP profile ↗ORCID search ↗
×2
Jiashu Xu
DBLP profile ↗ORCID search ↗
×2
Canyu Chen
DBLP profile ↗ORCID search ↗
×1
Guangwei Zhang
DBLP profile ↗ORCID search ↗
×1
Shawn Li
DBLP profile ↗ORCID search ↗
×1
Weidi Luo
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Can Editing LLMs Inject Harm?
    AAAI 2026 ·
    Canyu Chen
    DBLP profile ↗ORCID search ↗
  2. Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks
    ACL 2026 ·
    Guangwei Zhang
    DBLP profile ↗ORCID search ↗
  3. Defenses Against Prompt Attacks Learn Surface Heuristics
    ACL 2026 ·
    Shawn Li
    DBLP profile ↗ORCID search ↗
  4. AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
    ACL 2025 ·
    Weidi Luo
    DBLP profile ↗ORCID search ↗
  5. AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
    ICLR 2025 ·
    Xiaogeng Liu
    DBLP profile ↗ORCID search ↗
  6. Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
    ICLR 2025 ·
    Yingzi Ma
    DBLP profile ↗ORCID search ↗
  7. CVE-Bench: Benchmarking LLM-based Software Engineering Agent's Ability to Repair Real-World CVE Vulnerabilities
    NAACL 2025 ·
    Peiran Wang
    DBLP profile ↗ORCID search ↗
  8. Can Watermarks be Used to Detect LLM IP Infringement For Free?
    ICLR 2025 ·
    Zhengyue Zhao
    DBLP profile ↗ORCID search ↗
  9. DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
    NeurIPS 2025 ·
    Hao Li
    DBLP profile ↗ORCID search ↗
  10. DataGen: Unified Synthetic Dataset Generation via Large Language Models
    ICLR 2025 ·
    Yue Huang
    DBLP profile ↗ORCID search ↗
  11. DreamDrive: Generative 4D Scene Modeling from Street View Images
    ICRA 2025 ·
    Jiageng Mao
    DBLP profile ↗ORCID search ↗
  12. Eia: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
    ICLR 2025 ·
    Zeyi Liao
    DBLP profile ↗ORCID search ↗
  13. LeanAgent: Lifelong Learning for Formal Theorem Proving
    ICLR 2025 ·
    Adarsh Kumarappan
    DBLP profile ↗ORCID search ↗
  14. MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
    ICML 2025 ·
    Yaolun Zhang
    DBLP profile ↗ORCID search ↗
  15. MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
    ICLR 2025 ·
    Fei Wang
    DBLP profile ↗ORCID search ↗
  16. PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free
    ACL 2025 ·
    Hao Li
    DBLP profile ↗ORCID search ↗
  17. RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process
    NAACL 2025 ·
    Peiran Wang
    DBLP profile ↗ORCID search ↗
  18. Robust Representation Consistency Model via Contrastive Denoising
    ICLR 2025 ·
    Jiachen Lei
    DBLP profile ↗ORCID search ↗
  19. Sample-specific Noise Injection for Diffusion-based Adversarial Purification
    ICML 2025 ·
    Yuhao Sun
    DBLP profile ↗ORCID search ↗
  20. SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
    ACL 2025 ·
    Qin Liu
    DBLP profile ↗ORCID search ↗
  21. T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
    ICLR 2025 ·
    Zizheng Pan
    DBLP profile ↗ORCID search ↗
  22. Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
    NAACL 2025 ·
    Wenjie Jacky Mo
    DBLP profile ↗ORCID search ↗
  23. AdaShield : Safeguarding Multimodal Large Language Models from Structure-Based Attack via Adaptive Shield Prompting
    ECCV 2024 ·
    Yu Wang
    DBLP profile ↗ORCID search ↗
  24. AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
    NeurIPS 2024 ·
    Zhaorun Chen
    DBLP profile ↗ORCID search ↗
  25. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
    ICLR 2024 ·
    Xiaogeng Liu
    DBLP profile ↗ORCID search ↗
  26. BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
    NeurIPS 2024 ·
    Jiongxiao Wang
    DBLP profile ↗ORCID search ↗
  27. CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
    ICLR 2024 ·
    Jiachen Sun
    DBLP profile ↗ORCID search ↗
  28. ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger
    NAACL 2024 ·
    Jiazhao Li
    DBLP profile ↗ORCID search ↗
  29. Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
    NAACL 2024 ·
    Nan Xu
    DBLP profile ↗ORCID search ↗
  30. Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
    NeurIPS 2024 ·
    Yiquan Li
    DBLP profile ↗ORCID search ↗
  31. Conversational Drug Editing Using Retrieval and Domain Feedback
    ICLR 2024 ·
    Shengchao Liu
    DBLP profile ↗ORCID search ↗
  32. Dolphins: Multimodal Language Model for Driving
    ECCV 2024 ·
    Yingzi Ma
    DBLP profile ↗ORCID search ↗
  33. From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
    NAACL 2024 ·
    Qin Liu
    DBLP profile ↗ORCID search ↗
  34. HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
    NeurIPS 2024 ·
    Xuefeng Du
    DBLP profile ↗ORCID search ↗
  35. Instructional Fingerprinting of Large Language Models
    NAACL 2024 ·
    Jiashu Xu
    DBLP profile ↗ORCID search ↗
  36. Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
    NAACL 2024 ·
    Jiashu Xu
    DBLP profile ↗ORCID search ↗
  37. Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation
    ECCV 2024 ·
    Haizhong Zheng
    DBLP profile ↗ORCID search ↗
  38. Perada: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
    CVPR 2024 ·
    Chulin Xie
    DBLP profile ↗ORCID search ↗
  39. Position: TrustLLM: Trustworthiness in Large Language Models
    ICML 2024 ·
    Yue Huang
    DBLP profile ↗ORCID search ↗
  40. RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
    ACL 2024 ·
    Jiongxiao Wang
    DBLP profile ↗ORCID search ↗
  41. RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios
    ECCV 2024 ·
    Wenhao Ding
    DBLP profile ↗ORCID search ↗
  42. Reinforcement Learning with Human Feedback for Realistic Traffic Simulation
    ICRA 2024 ·
    Yulong Cao
    DBLP profile ↗ORCID search ↗