Tianwei Zhang

ShadeEdit: A Utility-Preserving and Defense-Evasive Knowledge Manipulation Attack in Federated LLMs AAAI 2026 VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking ICLR 2025 An LLM-Empowered Adaptive Evolutionary Algorithm for Multi-Component Deep Learning Systems AAAI 2025 TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models ICML 2025 BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach ICML 2025 A Benchmark for Semantic Sensitive Information in LLMs Outputs ICLR 2025 Understanding the Dark Side of LLMs’ Intrinsic Self-Correction ACL 2025 Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings ACL 2025 GPT-NER: Named Entity Recognition via Large Language Models NAACL 2025 Disco4D: Disentangled 4D Human Generation and Animation from a Single Image CVPR 2025 Hybrid Concept Bottleneck Models CVPR 2025 SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments CVPR 2025 Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems ICML 2025 When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models EMNLP 2025 Speculating LLMs’ Chinese Training Data Pollution from Their Tokens EMNLP 2025 Automated Red Teaming for Text-to-Image Models through Feedback-Guided Prompt Iteration with Vision-Language Models ICCV 2025 Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack ICCV 2025 An Engorgio Prompt Makes Large Language Model Babble on ICLR 2025 Characterization of Large Language Model Development in the Datacenter NSDI 2024 You Only Query Once: An Efficient Label-Only Membership Inference Attack ICLR 2024 ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users NIPS 2024 COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation NIPS 2024 Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation NIPS 2024 Robust-Wide: Robust Watermarking against Instruction-driven Image Editing ECCV 2024 Compilation and Fast Model Counting beyond CNF IJCAI 2024 Walking in Others’ Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias EMNLP 2024 Course-Correction: Safety Alignment Using Synthetic Preferences EMNLP 2024 AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA ICML 2024 Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation ICML 2024 BadEdit: Backdooring Large Language Models by Model Editing ICLR 2024 SAME: Sample Reconstruction against Model Extraction Attacks AAAI 2024 The Earth is Flat because...: Investigating LLMs’ Belief towards Misinformation via Persuasive Conversation ACL 2024 FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation ICLR 2024 State Chrono Representation for Enhancing Generalization in Reinforcement Learning NIPS 2024 Color Backdoor: A Robust Poisoning Attack in Color Space CVPR 2023 GNN-SL: Sequence Labeling Based on Nearest Examples via GNN ACL 2023 Hydro: Surrogate-Based Hyperparameter Tuning Service in Datacenters OSDI 2023 Computation and Data Efficient Backdoor Attacks ICCV 2023 GuardHFL: Privacy Guardian for Heterogeneous Federated Learning ICML 2023 Defending against Backdoor Attacks in Natural Language Generation AAAI 2023 Deep Multitask Learning with Progressive Parameter Sharing ICCV 2023 Extracting Robust Models with Uncertain Examples ICLR 2023 Text Classification via Large Language Models EMNLP 2023 One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training ICCV 2023 Towards Robust and Expressive Whole-body Human Pose and Shape Estimation NIPS 2023 Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only ICLR 2023 Multi-target Backdoor Attacks for Code Pre-trained Models ACL 2023 BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models ICLR 2022 Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms NIPS 2022 Fast Nearest Neighbor Machine Translation ACL 2022 Improving Adversarial Robustness of 3D Point Cloud Classification Models ECCV 2022 Iron: Private Inference on Transformers NIPS 2022 GNN-LM: Language Modeling based on Global Contexts via GNN ICLR 2022 NASPY: Automated Extraction of Automated Machine Learning Models ICLR 2022 Triggerless Backdoor Attack for NLP Tasks with Clean Labels NAACL 2022 Privacy-Preserving Collaborative Learning With Automatic Transformation Search CVPR 2021 Layer-wise Model Pruning based on Mutual Information EMNLP 2021 Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models IJCAI 2021 kFolden: k-Fold Ensemble for Out-Of-Distribution Detection EMNLP 2021 Learning to Optimize Non-Rigid Tracking CVPR 2020 Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning AAAI 2020 Sensitive-Sample Fingerprinting of Deep Neural Networks CVPR 2019