Profiles2021-2026
Han Qiu
Tsinghua University
30Papers
14Last author
45Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers30
- DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution ModelingAuthor 8 of 10S&P 2026 · 9 citations
- Revisiting the Reliability of Language Models in Instruction-FollowingAuthor 7 of 7ACL 2026 · 3 citations
- SafeSearch: Automated Red-Teaming of LLM-Based Search AgentsAuthor 9 of 9ICML 2026 · 3 citations
- Autoregressive-based Progressive Coding for Ultra-Low Bitrate Image CompressionAuthor 6 of 6ICLR 2026
- LeakDojo: Decoding the Leakage Threats of RAG SystemsAuthor 7 of 7ACL Findings 2026
- TOXIFRENCH: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity DetectionAuthor 4 of 5ACL Findings 2026
- Understanding the Dark Side of LLMs' Intrinsic Self-CorrectionAuthor 10 of 10ACL 2025 · 36 citations
- Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and FindingsAuthor 8 of 8ACL Findings 2025 · 4 citations
- "I've Decided to Leak": Probing Internals Behind Prompt Leakage IntentsAuthor 9 of 9EMNLP 2025 · 1 citation
- Speculating LLMs' Chinese Training Data Pollution from Their TokensAuthor 10 of 10EMNLP 2025 · 1 citation
- VISO: Accelerating In-Orbit Object Detection with Language-Guided Mask Learning and Sparse InferenceAuthor 2 of 2ICCV 2025 · 1 citation
- A Benchmark for Semantic Sensitive Information in LLMs OutputsAuthor 2 of 9ICLR 2025
- An Engorgio Prompt Makes Large Language Model Babble onAuthor 10 of 10ICLR 2025
- DCDiff: Enhancing JPEG Compression via Diffusion-based DC Coefficients EstimationAuthor 2 of 4DAC 2025
- VideoShield: Regulating Diffusion-based Video Generation Models via WatermarkingAuthor 6 of 7ICLR 2025
- Backdooring Multimodal LearningAuthor 6 of 8S&P 2024 · 39 citations
- You Only Query Once: An Efficient Label-Only Membership Inference AttackAuthor 2 of 5ICLR 2024 · 20 citations
- Laser Shield: a Physical Defense with Polarizer against Laser Attacks on Autonomous Driving SystemsAuthor 8 of 8DAC 2024 · 3 citations
- VisionGuard: Secure and Robust Visual Perception of Autonomous Vehicles in PracticeAuthor 7 of 9CCS 2024 · 3 citations
- PhyScout: Detecting Sensor Spoofing Attacks via Spatio-temporal ConsistencyAuthor 5 of 6CCS 2024 · 2 citations
- Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and BiasAuthor 8 of 8EMNLP 2024 · 2 citations
- The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive ConversationAuthor 9 of 9ACL 2024
- One-bit Flip is All You Need: When Bit-flip Attack Meets Model TrainingAuthor 2 of 9ICCV 2023 · 33 citations
- Computation and Data Efficient Backdoor AttacksAuthor 3 of 4ICCV 2023 · 17 citations
- Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge ComputingAuthor 7 of 7INFOCOM 2023 · 8 citations
- Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural NetworksAuthor 4 of 9USENIX Security 2023
- Extracting Robust Models with Uncertain ExamplesAuthor 4 of 6ICLR 2023
- jTrans: jump-aware transformer for binary code similarity detectionAuthor 6 of 8ISSTA 2022 · 139 citations
- BET: black-box efficient testing for convolutional neural networksAuthor 2 of 7ISSTA 2022 · 18 citations
- Privacy-Preserving Collaborative Learning With Automatic Transformation SearchAuthor 4 of 6CVPR 2021
