Security and Privacy in Machine Learning and Artificial Intelligence (AI)
A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".
Deadline for manuscript submissions: closed (30 October 2024) | Viewed by 14134
Special Issue Editors
Interests: artificial intelligence security and privacy; cryptography, cloud computing security
Interests: blockchain; data privacy; information security; AI security
Interests: information security theory; secure multi-party computing protocols; blockchain and smart contract applications
Interests: machine learning; artificial intelligence; computer vision; human-computer interface
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
In the past decade, the world has witnessed a booming development in the field of Machine Learning (ML) and Artificial Intelligence (AI). Under this trend, ML&AI techniques have been increasingly deployed for automated decisions in many critical applications, such as autonomous vehicles, personalized recommendations, cybersecurity, health care, and many more. However, the use of ML&AI in security- and privacy-sensitive domains, where adversaries may attempt to mislead or evade intelligent mechanisms, creates new frontiers for security research. On the one hand, ML&AI technologies, especially deep learning, have been repeatedly proven to suffer from trust and interpretability challenges in the face of various attacks, such as adversarial attacks, poisoning attacks, backdoor attacks, member inference, member reconstruction, etc. Therefore, new ML&AI theories and methods are required to ensure security and data privacy. On the other hand, to overcome the efficiency and application limitation of simple data encryption solutions, new security, and privacy technologies are necessary to exploit, such as federated learning, homomorphic encryption, differential privacy, secure multiparty computation, and many more. Moreover, with the promulgation of security and privacy legislation, such as the General Data Protection Regulation (GDPR), more restrictions are required for data owners, enterprises, and organizations in collecting, using, sharing, and managing Internet data. Therefore, how to ensure the security and privacy of the systems enabled by ML&AI techniques is becoming urgent and challenging.
This Special Issue is expected to publish high-quality and original papers presenting novel algorithms, protocols, or systems that enhance the security and privacy protections of the emerging ML&AI paradigm. Potential topics include, but are not limited to, the following research areas:
ML&AI Theoretical topics:
- ML&AI interpretability
- adversarial learning
- differential privacy for ML&AI
- cryptography for ML&AI
Application topics:
- evasion attacks and defenses
- poisoning attack and defenses
- model inversion attacks and defenses
- AI backdoors attacks and defenses
- membership inference/reconstruction attacks and defenses
- digital watermarking for ML&AI models
- privacy-preserving data mining
- privacy-preserving data publishing
- ML&AI model processing platforms
- ML&AI-based social networks security and privacy
- ML&AI-based secure and privacy-preserving blockchain
- secure and privacy-preserving outsourced ML&AI
- security and privacy of federated machine learning
- AI-based detection techniques, e.g., intrusion detection, anomaly detection, fraud detection, malicious codes, network anomalous behaviors, etc.
Other topics:
- ML&AI fairness
- ML&AI trust
- ML&AI ethics
Dr. Tao Jiang
Dr. Yuling Chen
Prof. Dr. Yilei Wang
Prof. Dr. Huiyu (Joe) Zhou
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. Applied Sciences 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 2400 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.
Keywords
- machine learning and artificial intelligence
- security and privacy
- cryptography
- attack and defense
- theory and application
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.
Further information on MDPI's Special Issue polices can be found here.