Securing Artificial Intelligence Against Attacks
A special issue of Future Internet (ISSN 1999-5903).
Deadline for manuscript submissions: 31 May 2025 | Viewed by 9
Special Issue Editors
Interests: IT security; privacy; interactive machine learning
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
In recent years, AI has started to permeate many fields and industries with affordable and scalable services. Expectations are high that this trend will continue for a while, providing new AI-based services to experts and the general public alike, but also bringing change to many classical approaches, which can be enhanced greatly with AI.
This, of course, opens up new attack surfaces and attack vectors, using AI as both a tool for attacks, but also as a target. The latter is especially important, as currently prominent AI technologies like LLMs and DNNs lack explainability and thus also transparency. Furthermore, many classical security approaches like penetration testing need to be adapted to this situation, as, e.g., translating the finding of a security-relevant error in an AI system into a fix is generally not possible for many currently employed algorithms. In addition, complex systems like neural networks might increase the attack surface quite drastically, requiring special treatment not only from a technical perspective, but also from a risk management one.
This Special Issue is dedicated to research results in the area of security for AI systems. It calls for cutting-edge contributions to fundamental theoretical research as well as its application in practice. This Special Issue covers, but is not limited to, the following topics:
- Attacks against AI systems, e.g., model and data poisoning and model extraction attacks;
- Privacy and AI;
- Trustworthy AI and trust in data-driven systems;
- Controllable AI;
- Secure and trustworthy data provisioning;
- Resilient data-driven systems;
- AI risk analysis and AI risk management;
- Implementing security requirements from the AI Act;
- Security testing AI, e.g., penetration testing;
- Proof of concepts for secure AI systems.
Prof. Dr. Peter Kieseberg
Prof. Dr. Jungwoo Ryoo
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. Future Internet is an international peer-reviewed open access monthly 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 1600 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
- AI
- trustworthy AI
- AI attacks
- attacking AI
- secure AI
- controllable AI
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.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
