23 citations · 38 across the 15 of their papers we have counts for
16 papers
What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?
Boyang Ma, Hechuan Guo, Peizhuo Lv +5
Embodied AI systems (e.g., autonomous vehicles, service robots, and LLM-driven interactive agents) are rapidly transitioning from controlled environments to safety critical real-wo…
Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Faces
Junyu Shi, Minghui Li, Junguo Zuo +8
Deepfakes, leveraging advanced AIGC (Artificial Intelligence-Generated Content) techniques, create hyper-realistic synthetic images and videos of human faces, posing a significant…
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
Wei Wan, Yuxuan Ning, Zhicong Huang +7
Federated Learning (FL) is a distributed paradigm aimed at protecting participant data privacy by exchanging model parameters to achieve high-quality model training. However, this…
Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
Minghui Li, Hao Zhang, Yechao Zhang +4
Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address th…
Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM
Lei Yu, Yechao Zhang, Ziqi Zhou +6
With the rapid development of the Vision-Language Model (VLM), significant progress has been made in Visual Question Answering (VQA) tasks. However, existing VLM often generate ina…
Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
Yechao Zhang, Yuxuan Zhou, Tianyu Li +4
Transfer learning from pre-trained encoders has become essential in modern machine learning, enabling efficient model adaptation across diverse tasks. However, this combination of…
Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization
Yechao Zhang, Yingzhe Xu, Junyu Shi +4
Deep neural networks (DNNs) are susceptible to universal adversarial perturbations (UAPs). These perturbations are meticulously designed to fool the target model universally across…
Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
Xianlong Wang, Minghui Li, Wei Liu +5
Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity informa…
ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification
Xianlong Wang, Shengshan Hu, Yechao Zhang +5
Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victi…
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
Ziqi Zhou, Minghui Li, Wei Liu +7
With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trai…
Robust Backdoor Detection for Deep Learning via Topological Evolution Dynamics
Xiaoxing Mo, Yechao Zhang, Leo Yu Zhang +5
A backdoor attack in deep learning inserts a hidden backdoor in the model to trigger malicious behavior upon specific input patterns. Existing detection approaches assume a metric…
AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning
Ziqi Zhou, Shengshan Hu, Minghui Li +3
Multimodal contrastive learning aims to train a general-purpose feature extractor, such as CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit…
Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
Yechao Zhang, Shengshan Hu, Leo Yu Zhang +5
Adversarial examples (AEs) for DNNs have been shown to be transferable: AEs that successfully fool white-box surrogate models can also deceive other black-box models with different…
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
Shengshan Hu, Ziqi Zhou, Yechao Zhang +4
Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonst…
Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer
Shengshan Hu, Xiaogeng Liu, Yechao Zhang +4
While deep face recognition (FR) systems have shown amazing performance in identification and verification, they also arouse privacy concerns for their excessive surveillance on us…
Towards Efficient Data-Centric Robust Machine Learning with Noise-based Augmentation
Xiaogeng Liu, Haoyu Wang, Yechao Zhang +2
The data-centric machine learning aims to find effective ways to build appropriate datasets which can improve the performance of AI models. In this paper, we mainly focus on design…