Privacy-Preserving and Models Intrusion Detection Federated Deep Learning Challenges, Schemas and Future Trajectories

Abstract

Deep learning has made remarkable research advancements and wide-ranging applications in the domains of computer vision, multimodal, natural language processing, additionally, other areas. This has caused the academic community to pay increasingly close attention to the attack and defense technology in its training and testing phases, among which the federal deep learning has produced positive results. Federated deep learning models are prone to memorizing private and sensitive terminal participants' data, model parameters, when combined with the model's inherent vulnerability, they will result in privacy leakage, poisoning attack, model inference attack, adversarial attack. We briefly discuss the conception of federated deep learning as well as security challenges and open questions in this paper. In order to facilitate the understanding of these challenges and problems, we further propose a security system model. We also provide an overview and deduce the attack and mitigation approaches to the most sophisticated privacy-preserving and intrusion detection models. in the last two years. To tackle these challenges and enlighten further encryption techniques researches, finally, we discuss and describe current prospects and future trajectories of federated deep learning.