2 citations · 6 across the 29 of their papers we have counts for
15 papers · 1 filter
Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure
Lulu Xue, Shengshan Hu, Linqiang Qian +6
Machine unlearning is a newly popularized technique for removing specific training data from a trained model, enabling it to comply with data deletion requests. While it protects t…
UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
Hewen Pan, Cong Wei, Dashuang Liang +8
With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existi…
SegTrans: Transferable Adversarial Examples for Segmentation Models
Yufei Song, Ziqi Zhou, Qi Lu +6
Segmentation models exhibit significant vulnerability to adversarial examples in white-box settings, but existing adversarial attack methods often show poor transferability across…
DarkHash: A Data-Free Backdoor Attack Against Deep Hashing
Ziqi Zhou, Menghao Deng, Yufei Song +6
Benefiting from its superior feature learning capabilities and efficiency, deep hashing has achieved remarkable success in large-scale image retrieval. Recent studies have demonstr…
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…
ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
Yichen Wang, Hangtao Zhang, Hewen Pan +7
Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous…
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…
Towards Reliable Forgetting: A Survey on Machine Unlearning Verification
Lulu Xue, Shengshan Hu, Wei Lu +7
With growing demands for privacy protection, security, and legal compliance (e.g., GDPR), machine unlearning has emerged as a critical technique for ensuring the controllability an…
Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning
Peijin Guo, Minghui Li, Hewen Pan +6
Accurate prediction of molecular metabolic stability (MS) is critical for drug research and development but remains challenging due to the complex interplay of molecular interactio…
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…
Multi-Modality Representation Learning for Antibody-Antigen Interactions Prediction
Peijin Guo, Minghui Li, Hewen Pan +6
While deep learning models play a crucial role in predicting antibody-antigen interactions (AAI), the scarcity of publicly available sequence-structure pairings constrains their ge…
Test-Time Backdoor Detection for Object Detection Models
Hangtao Zhang, Yichen Wang, Shihui Yan +7
Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. De…
PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
Yufei Song, Ziqi Zhou, Minghui Li +6
With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, \ie, adversarial attacks on deep neural networks. Existing works primar…