36 citations · 70 across the 16 of their papers we have counts for
16 papers
Imperceptible Jailbreaking against Large Language Models
Kuofeng Gao, Yiming Li, Chao Du +4
Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visi…
Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models
Kuofeng Gao, Yufei Zhu, Yiming Li +4
Text-to-image (T2I) diffusion models enable high-quality image generation conditioned on textual prompts. However, fine-tuning these pre-trained models for personalization raises c…
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
Sheng Yang, Jiawang Bai, Kuofeng Gao +3
Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tas…
Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
Mingyan Zhu, Yiming Li, Junfeng Guo +3
Currently, sample-specific backdoor attacks (SSBAs) are the most advanced and malicious methods since they can easily circumvent most of the current backdoor defenses. In this pape…
Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
Junfeng Guo, Yiming Li, Lixu Wang +4
The prosperity of deep neural networks (DNNs) is largely benefited from open-source datasets, based on which users can evaluate and improve their methods. In this paper, we revisit…
One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training
Jianshuo Dong, Han Qiu, Yiming Li +5
Deep neural networks (DNNs) are widely deployed on real-world devices. Concerns regarding their security have gained great attention from researchers. Recently, a new weight modifi…
Defending Against Backdoor Attacks by Layer-wise Feature Analysis
Najeeb Moharram Jebreel, Josep Domingo-Ferrer, Yiming Li
Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third pa…
BackdoorBox: A Python Toolbox for Backdoor Learning
Yiming Li, Mengxi Ya, Yang Bai +2
Third-party resources (, samples, backbones, and pre-trained models) are usually involved in the training of deep neural networks (DNNs), which brings backdoor attacks as a n…
Untargeted Backdoor Attack against Object Detection
Chengxiao Luo, Yiming Li, Yong Jiang +1
Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backd…
BATT: Backdoor Attack with Transformation-based Triggers
Tong Xu, Yiming Li, Yong Jiang +1
Deep neural networks (DNNs) are vulnerable to backdoor attacks. The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoor…
MOVE: Effective and Harmless Ownership Verification via Embedded External Features
Yiming Li, Linghui Zhu, Xiaojun Jia +5
Currently, deep neural networks (DNNs) are widely adopted in different applications. Despite its commercial values, training a well-performing DNN is resource-consuming. Accordingl…
Defending against Model Stealing via Verifying Embedded External Features
Yiming Li, Linghui Zhu, Xiaojun Jia +3
Obtaining a well-trained model involves expensive data collection and training procedures, therefore the model is a valuable intellectual property. Recent studies revealed that adv…
Regional Adversarial Training for Better Robust Generalization
Chuanbiao Song, Yanbo Fan, Yichen Yang +4
Adversarial training (AT) has been demonstrated as one of the most promising defense methods against various adversarial attacks. To our knowledge, existing AT-based methods usuall…
Backdoor Attack in the Physical World
Yiming Li, Tongqing Zhai, Yong Jiang +2
Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdo…
Backdoor Attack against Speaker Verification
Tongqing Zhai, Yiming Li, Ziqi Zhang +3
Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount o…
Multinomial Random Forest: Toward Consistency and Privacy-Preservation
Yiming Li, Jiawang Bai, Jiawei Li +4
Despite the impressive performance of random forests (RF), its theoretical properties have not been thoroughly understood. In this paper, we propose a novel RF framework, dubbed mu…