Multidomain active defense: Detecting multidomain backdoor poisoned samples via ALL-to-ALL decoupling training without clean datasets.

Deep learning is vulnerable to backdoor poisoning attacks in which an attacker can easily embed a hidden backdoor into a trained model by injecting poisoned samples into the training set. Many prior state-of-the-art techniques for detecting backdoor poisoning attacks are based on a potential separability assumption. However, current adaptive poisoning strategies can significantly reduce 'distinguishable behavior', making most prior state-of-the-art techniques less effective. In addition, we note that existing detection methods are not practical for multidomain datasets and may leak user privacy because they require and collect clean samples. To address the above issues, we propose a multidomain active defense approach that does not use clean datasets. The proposed approach can generate diverse clean samples from different domains and decouple neural networks round by round using clean samples to disassociate features and labels, making backdoor poisoned samples easier to detect without fitting clean samples. We demonstrate the advantage of our approach through an extensive evaluation of CIFAR10, CelebA, MNIST & MNIST-M, MNIST & USPS & MNIST-M, MNIST & USPS & SVHN and CIFAR10 & Tiny-ImageNet.

A secure and decentralized SSI authentication protocol with privacy protection and fine-grained access control based on federated blockchain.

Self-sovereign identity authentication protocol is an active research topic in the field of identity authentication and management. However, the current SSI authentication protocols pay little attention to privacy protection and the fine-grained access control. Therefore, a secure and decentralized SSI authentication protocol with privacy protection and fine-grained access control is proposed. Firstly, the formal model of SSI including the SDPP-SSI identity model and management model is presented. And then, based on the federated blockchain, the distributed identifier is used as a global identifier for users in the decentralized domain. Finally, the verifiable statement is encapsulated using a policy control signature supporting privacy protection to develop the user's access control for identity registration in the centralized domain. Compared with the related work (Lin 2018, Zhu 2018, Stokkink 2018, Hammudoglu 2017, Othman 2017, Abraham 2018, Guan 2019, Lin 2019) from controllability, security, flexibility, privacy protection, authentication and fine-grained access control, the proposed SSI authentication protocol not only meets controllability, authentication, and flexibility, but also supports privacy protection and fine-grained access control.