Author

Kuofeng Gao

Observed names: Gao, Kuofeng, kuofeng Gao

Institutions: Dalian University of Technology, University Town of Shenzhen, Tsinghua–Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University

Observed institutions: Tencent (China), Dalian University of Technology, University Town of Shenzhen, Tsinghua–Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University

ORCID: 0000-0002-5667-8238

Observed ORCID: 0000-0002-5667-8238

OpenAlex ID: A5038862367

Backdoor Defense via Adaptively Splitting Poisoned Dataset

2023 · Kuofeng Gao, Yang Bai, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 62

PDF

Imperceptible and Robust Backdoor Attack in 3D Point Cloud

2023 · Kuofeng Gao, Jiawang Bai, et al. · IEEE Transactions on Information Forensics and Security · 45

PDF

Hardly Perceptible Trojan Attack Against Neural Networks with Bit Flips

2022 · Jiawang Bai, Kuofeng Gao, et al. · Lecture notes in computer science · 29

PDF

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP

2024 · Jiawang Bai, Kuofeng Gao, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 28

PDF

Deconstructing the ethics of large language models from long-standing issues to new-emerging dilemmas: a survey

2025 · Chengyuan Deng, Yiqun Duan, et al. · AI and Ethics · 26

PDF

PointNCBW: Toward Dataset Ownership Verification for Point Clouds via Negative Clean-Label Backdoor Watermark

2024 · Cheng Wei, Yang Wang, et al. · IEEE Transactions on Information Forensics and Security · 13

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers

2024 · Sheng Yang, Jiawang Bai, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 9

Practical protection against video data leakage via universal adversarial head

2022 · Jiawang Bai, Bin Chen, et al. · Pattern Recognition · 7

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images

2024 · Gao, Kuofeng, Bai, Yang, et al. · arXiv (Cornell University) · 6

PDF

VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service

2025 · Xiasi Wang, Tianliang Yao, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 5

PDF

Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning

2021 · Gao, Kuofeng, Bai, Jiawang, et al. · arXiv (Cornell University) · 5

PDF

Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations

2025 · Haitong Liu, Kuofeng Gao, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 4

Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models

2025 · Kuofeng Gao, Shu-Tao Xia, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 4

PDF

QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language

2025 · Qingsong Zou, Jingyu Xiao, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 4

PDF

Toward Dataset Copyright Evasion Attack Against Personalized Text-to-Image Diffusion Models

2025 · Kuofeng Gao, Yufei Zhu, et al. · IEEE Transactions on Information Forensics and Security · 3

Denial-of-Service Poisoning Attacks against Large Language Models

2024 · Gao, Kuofeng, Pang, Tianyu, et al. · arXiv (Cornell University) · 3

PDF

Adversarial Robustness for Visual Grounding of Multimodal Large Language Models