Decentralized machine learning involves training models on distributed data sources, often without directly sharing the raw data. As the field of machine learning expands and embraces decentralized architectures, ensuring the security of decentralized machine learning becomes crucial. Decentralized machine learning security focuses on developing innovative techniques, algorithms, and frameworks to guarantee the privacy, integrity, and confidentiality of decentralized machine learning systems. It involves developing mechanisms to prevent privacy leakage and unauthorized access to sensitive data during the training process. Ensuring the reliability and trustworthiness of the participants is crucial to prevent adversarial attacks or manipulation of the training process. Additionally, decentralized machine learning security involves addressing resource constraints, optimizing computation and communication overhead, and mitigating the risks associated with system vulnerabilities and attacks.

Distributed Machine Learning Security is an important research area that aims to address the security challenges arising from the distributed nature of machine learning systems. By developing robust privacy-preserving techniques, protecting the integrity of models, and securing the communication infrastructure, researchers are working towards enabling the widespread adoption of distributed machine learning in various sensitive domains while ensuring data privacy and model security.

Topics of Interest

This workshop aims to provide a forum for international researchers from both academia and industry to exchange ideas, and discuss novel ideas, theories, frameworks, and testbeds for the promotion of decentralized machine learning security. The topics of interest include, but are not limited to, the following:

Privacy-preserving techniques for decentralized machine learning
Secure multi-party computation in distributed machine learning
Detection and mitigation of data poisoning attacks in decentralized learning
Trustworthiness and reputation management in decentralized machine learning
Secure communication protocols for decentralized machine learning settings
Anomaly detection and intrusion detection in distributed machine learning
Scalability and efficiency of security mechanisms in decentralized machine learning
Resource-constrained security for decentralized machine learning
Cryptographic protocols for secure data sharing in decentralized learning
Standardization and interoperability of decentralized machine learning security
Real-world applications and case studies in decentralized machine learning security
Adversarial attacks and defenses in decentralized machine learning

The workshop will feature 1-2 keynote speeches given by world-leading researchers in the field. The workshop accepts only original and unpublished papers. Submitted papers must not substantially overlap with papers that have been published or that are simultaneously submitted to a journal or a conference with proceedings. The work must be clearly presented in English in Springer LNCS Format. The total length of the final papers is at most 20 pages (for regular papers) and 12 pages (for short papers), including tables, figures, references and appendices. Papers will be selected based on their originality, significance, timeliness, relevance, and clarity of presentation assessed by at least three reviewers.

Important Dates

Paper Submission Due 30 May 2024 
Author Notification 30 July 2024
Camera-ready for Accepted Paper Due 10 September 2024
Conference Date 29-31 October 2024