Trustworthy AI: Security, Safety and Privacy
A Special Issue of Applied Sciences (ISSN 2076-3417) belonging to the section "Computing and Artificial Intelligence".
Deadline for manuscript submissions: 20 February 2027 | Viewed by 360
Editors
Interests: trustworthy ML; responsible AI; AI copyright protection
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Artificial intelligence (AI) technology has been deeply integrated into a wide range of applications, including autonomous driving, healthcare, and natural language processing. In particular, the advent of generative AI has enabled models to produce human-like content with remarkable fidelity, dramatically broadening the practical deployment of AI systems. More recently, the emergence of AI agents, which are systems capable of autonomously perceiving environments, planning multi-step actions, invoking external tools, and executing complex tasks with minimal human intervention, has further expanded the frontier of AI applications, from intelligent personal assistants and automated scientific discovery to multi-agent collaborative systems. However, these rapid advances also amplify existing security concerns. AI systems, including both conventional models and agentic pipelines, face significant threats such as adversarial vulnerability, backdoor attacks, fairness violations, and privacy breaches. In agentic settings, these risks are further compounded: an agent's ability to autonomously interact with external environments and chain together sequences of actions means that a single compromised component can propagate failures across an entire pipeline. Due to the inherent complexity and limited interpretability of deep neural networks, detecting and mitigating such risks remains a formidable challenge. This challenge is especially acute in safety-critical domains such as aerospace, intelligent medicine, and unmanned aerial vehicles, where the trustworthiness, reliability, and interpretability of AI systems are of paramount importance. Consequently, ensuring the safety and security of AI, spanning both foundational models and emerging agentic systems, has become a central research priority and a pressing concern for the international AI community.
This Special Issue will consolidate research efforts to identify security and privacy challenges in AI models and systems, develop secure and robust AI algorithms and protocols, and create fairness- and copyright-preserving techniques. We invite prospective authors to submit original research contributions on topics including, but not limited to, the following:
1. Safety, Security, Privacy of AI Agents.
2. Jailbreak Attacks and Defenses for Large Models;
3. The hallucination of Large Language Models;
4. AIGC Detection and Attribution;
5. Adversarial Attacks and Defenses for AI;
6. Backdoor Attacks and Defenses for AI;
7. Data Poisoning Attacks and Defenses for AI;
8. Copyright Issues in AI;
9. Privacy Issues in AI;
10. Fairness Issues in AI;
11. Model Interpretability and its Applications in AI Security.
Dr. Yiming Li
Dr. Zhongliang Guo
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 250 words) can be sent to the Editorial Office for assessment.
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-anonymized 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
- trustworthy ML
- responsible AI
- AI security
- LLM safety
- agent safety
- AI copyright protection
- fairness and privacy
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.
