424 citations · 1.1k across the 25 of their papers we have counts for
9 papers · 1 filter
FedMobile: Enabling Knowledge Contribution-aware Multi-modal Federated Learning with Incomplete Modalities
Yi Liu, Cong Wang, Xingliang Yuan
The Web of Things (WoT) enhances interoperability across web-based and ubiquitous computing platforms while complementing existing IoT standards. The multimodal Federated Learning…
Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts
Yi Liu, Chengjun Cai, Xiaoli Zhang +2
Large Vision Language Models (VLMs) extend and enhance the perceptual abilities of Large Language Models (LLMs). Despite offering new possibilities for LLM applications, these adva…
Unraveling Privacy Risks of Individual Fairness in Graph Neural Networks
He Zhang, Xingliang Yuan, Shirui Pan
Graph neural networks (GNNs) have gained significant attraction due to their expansive real-world applications. To build trustworthy GNNs, two aspects - fairness and privacy - have…
Trustworthy Graph Neural Networks: Aspects, Methods and Trends
He Zhang, Bang Wu, Xingliang Yuan +3
Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation syst…
Projective Ranking-based GNN Evasion Attacks
He Zhang, Xingliang Yuan, Chuan Zhou +1
Graph neural networks (GNNs) offer promising learning methods for graph-related tasks. However, GNNs are at risk of adversarial attacks. Two primary limitations of the current evas…
Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications
Bang Wu, Xiangwen Yang, Shirui Pan +1
Graph Neural Networks (GNNs) are widely adopted to analyse non-Euclidean data, such as chemical networks, brain networks, and social networks, modelling complex relationships and i…
Poisoning Semi-supervised Federated Learning via Unlabeled Data: Attacks and Defenses
Yi Liu, Xingliang Yuan, Ruihui Zhao +3
Semi-supervised Federated Learning (SSFL) has recently drawn much attention due to its practical consideration, i.e., the clients may only have unlabeled data. In practice, these S…
Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization
Bang Wu, Xiangwen Yang, Shirui Pan +1
Machine learning models are shown to face a severe threat from Model Extraction Attacks, where a well-trained private model owned by a service provider can be stolen by an attacker…
Defeating Misclassification Attacks Against Transfer Learning
Bang Wu, Shuo Wang, Xingliang Yuan +3
Transfer learning is prevalent as a technique to efficiently generate new models (Student models) based on the knowledge transferred from a pre-trained model (Teacher model). Howev…