Chaowei Xiao

Can Editing LLMs Inject Harm? AAAI 2026 Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks ACL 2026 Defenses Against Prompt Attacks Learn Surface Heuristics ACL 2026 T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching ICLR 2025 AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs ICLR 2025 Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset ICLR 2025 Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations NAACL 2025 Can Watermarks be Used to Detect LLM IP Infringement For Free? ICLR 2025 MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines ICML 2025 Sample-specific Noise Injection for Diffusion-based Adversarial Purification ICML 2025 RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process NAACL 2025 AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection ACL 2025 SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment ACL 2025 PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free ACL 2025 Robust Representation Consistency Model via Contrastive Denoising ICLR 2025 EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE ICLR 2025 MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding ICLR 2025 DataGen: Unified Synthetic Dataset Generation via Large Language Models ICLR 2025 CVE-Bench: Benchmarking LLM-based Software Engineering Agent’s Ability to Repair Real-World CVE Vulnerabilities NAACL 2025 LeanAgent: Lifelong Learning for Formal Theorem Proving ICLR 2025 Instructional Fingerprinting of Large Language Models NAACL 2024 BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NIPS 2024 HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection NIPS 2024 Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness NIPS 2024 AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases NIPS 2024 RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models ACL 2024 PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees CVPR 2024 AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting ECCV 2024 Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation ECCV 2024 Dolphins: Multimodal Language Model for Driving ECCV 2024 RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios ECCV 2024 AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models ICLR 2024 Conversational Drug Editing Using Retrieval and Domain Feedback ICLR 2024 CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception ICLR 2024 Position: TrustLLM: Trustworthiness in Large Language Models ICML 2024 From Shortcuts to Triggers: Backdoor Defense with Denoised PoE NAACL 2024 ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger NAACL 2024 Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models NAACL 2024 Combating Security and Privacy Issues in the Era of Large Language Models NAACL 2024 Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking NAACL 2024 Differentially Private Video Activity Recognition WACV 2024 Retrieval-based Controllable Molecule Generation ICLR 2023 Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study EMNLP 2023 Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency CVPR 2023 VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion CVPR 2023 A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification ICML 2023 CodeIPPrompt: Intellectual Property Infringement Assessment of Code Language Models ICML 2023 On the Exploitability of Instruction Tuning NIPS 2023 Defending against Insertion-based Textual Backdoor Attacks via Attribution ACL 2023 HiCL: Hierarchical Contrastive Learning of Unsupervised Sentence Embeddings EMNLP 2023 Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning EMNLP 2023 DensePure: Understanding Diffusion Models for Adversarial Robustness ICLR 2023 Defending against Adversarial Audio via Diffusion Model ICLR 2023 Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models NIPS 2022 Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models NIPS 2022 RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning ICLR 2022 Understanding The Robustness in Vision Transformers ICML 2022 AdvDO: Realistic Adversarial Attacks for Trajectory Prediction ECCV 2022 SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination ECCV 2022 Robust Trajectory Prediction against Adversarial Attacks CORL 2022 Diffusion Models for Adversarial Purification ICML 2022 Long-Short Transformer: Efficient Transformers for Language and Vision NIPS 2021 Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings? ICCV 2021 Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions NIPS 2021 AugMax: Adversarial Composition of Random Augmentations for Robust Training NIPS 2021 Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations NIPS 2020 SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing ECCV 2020 Towards Stable and Efficient Training of Verifiably Robust Neural Networks ICLR 2020 AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos ICCV 2019 MeshAdv: Adversarial Meshes for Visual Recognition CVPR 2019 Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation ECCV 2018 Spatially Transformed Adversarial Examples ICLR 2018 Robust Physical-World Attacks on Deep Learning Visual Classification CVPR 2018 Generating Adversarial Examples with Adversarial Networks IJCAI 2018