Konferenzen  >  Informatik  >  Informationssicherheit und Datenschutz  >  Japan

ACNS is an annual conference focusing on current developments that advance the areas of applied cryptography, cyber security (including network and computer security) and privacy. The goal is to represent both academic research works as well as developments in industrial and technical frontiers. Submissions may focus on the modelling, design, analysis (including security proofs and attacks), development (e.g. implementations), deployment (e.g. system integration), and maintenance (e.g. performance measurements, usability studies) of algorithms, protocols, standards, implementations, technologies devices, systems standing in relation with applied cryptography, cyber security and privacy, while advancing or bringing new insights to the state of the art.

Kryptographie, Blockchain und Informationssicherheit,    Netzwerke, Internet

in conjunction with ACNS 2023

Despite the promise in data protection, federated learning faces new security and privacy threats. Some recent research has shown that it is possible to infer training data information by observing shared models. In addition, there is strong desire to protect models because model design needs significant investment and they are treated as important digital assets. However, models are exposed to everyone in the default design of federated learning. Furthermore, malicious participants may exist in federated learning and they would compromise the whole learning process by sharing wrong models. There also may exist free-riders that enjoy the shared model, without making contributions. Addressing the above challenges of federated learning security and privacy needs significant research efforts on theories, algorithms, architecture, and experiences of system deployment and maintenance. Therefore, this workshop aims to offer a platform for researchers from both academia and industry to publish recent research findings and to discuss opportunities, challenges and solutions related to security and privacy of federated learning.