Security and Privacy for Machine Learning Applications

Dear Colleagues,

Artificial intelligence and machine learning are playing a key role in developing cybersecurity tools to protect cyberphysical infrastructure from malicious actors. Currently, these technologies are being used in a multitude of domains to automate tasks such as driving, diagnostics, trading, marketing, and many more. As we rely heavily on artificial intelligence and machine learning for our day-to-day activities, it is paramount to protect these technologies from emerging cyber threats. Machine learning models were built using a huge amount of high-quality and application-specific data. Even though machine learning models can only be trained at places where data are available, anyone can use the trained model for classification tasks via the internet. While this looks revolutionary, trained machine learning models are not readily available to users in sectors such as healthcare, finance, or marketing due to privacy issues. Users do not want to share their sensitive data with service providers due to a lack of trust. Privacy legislation such as the General Data Protection Regulation (GDPR) restricts data organizations from sharing with other institutes. Moreover, several security threats, such as adversarial generative networks, pose serious threats to the reliability of these models being used in high-stake applications, such as autonomous vehicles and medical diagnostics. A trusted framework is required for machine learning systems to ensure security and data privacy. This will boost confidence in consumers who want to use machine learning services without security and privacy worries. Simply encrypting data only protects them during storage and transmission. Hence, federated learning, fully homomorphic encryption, differential privacy, secure multiparty computation, and many more novel technologies are being exploited to uphold the security and privacy of machine learning algorithms. This Special Issue is expected to receive papers presenting novel algorithms to mitigate security and privacy threats to the emerging artificial intelligence and machine learning paradigm. Potential topics include, but are not limited to, the following research areas:

1. Privacy-preserving techniques
2. Encrypted computation
3. Machine learning in encrypted domain
4. Homomorphic encryption for machine learning
5. Secure multi-party computation and federated learning
6. Security and privacy of federated machine learning

Dr. Yogachandran Rahulamathavan
Dr. Beibei Li
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.