4 citations · 6 across the 13 of their papers we have counts for
9 papers · 1 filter
Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models
Kai Wang, Jiale Zhang, Chengcheng Zhu +2
Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus m…
BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS
Ye Li, Chengcheng Zhu, Yanchao Zhao +1
In this paper, we endeavor to address the challenges of backdoor attacks countermeasures in black-box scenarios, thereby fortifying the security of inference under MLaaS. We first…
Towards Generalized and Stealthy Watermarking for Generative Code Models
Haoxuan Li, Jiale Zhang, Xiaobing Sun +1
Generative code models (GCMs) significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models req…
SPA: Towards More Stealth and Persistent Backdoor Attacks in Federated Learning
Chengcheng Zhu, Ye Li, Bosen Rao +3
Federated Learning (FL) has emerged as a leading paradigm for privacy-preserving distributed machine learning, yet the distributed nature of FL introduces unique security challenge…
BDPFL: Backdoor Defense for Personalized Federated Learning via Explainable Distillation
Chengcheng Zhu, Jiale Zhang, Di Wu +1
Federated learning is a distributed learning paradigm that facilitates the collaborative training of a global model across multiple clients while preserving the privacy of local da…
"No Matter What You Do": Purifying GNN Models via Backdoor Unlearning
Jiale Zhang, Chengcheng Zhu, Bosen Rao +5
Recent studies have exposed that GNNs are vulnerable to several adversarial attacks, among which backdoor attack is one of the toughest. Similar to Deep Neural Networks (DNNs), bac…
DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networks
Hao Sui, Bing Chen, Jiale Zhang +4
Recent studies have revealed that GNNs are highly susceptible to multiple adversarial attacks. Among these, graph backdoor attacks pose one of the most prominent threats, where att…
Beyond Dataset Watermarking: Model-Level Copyright Protection for Code Summarization Models
Jiale Zhang, Haoxuan Li, Di Wu +3
Code Summarization Model (CSM) has been widely used in code production, such as online and web programming for PHP and Javascript. CSMs are essential tools in code production, enha…
Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning
Ye Li, Yanchao Zhao, Chengcheng Zhu +1
Federated Learning (FL), a privacy-preserving decentralized machine learning framework, has been shown to be vulnerable to backdoor attacks. Current research primarily focuses on t…