Topics of interest include the following related to AI Security and Privacy
Adversarial learning
Federated learning
Machine Unlearning
AI approaches to trust and reputation
AI Misuse (e.g. misinformation, deepfakes)
Machine learning and computer security
Privacy-enhancing technologies, anonymity, and censorship (e.g. Differential privacy in AI)
Also this workshop, AI Security and Privacy, is interested in all AI aspects of computer security and privacy. And , we include the following LLM-related hot topics such as
Secure Large AI Systems and Models
Large AI Systems and Models' Privacy and Security Vulnerabilities
Copyright of AI
while covering any aspect of AI Safety including, but not limited to:
Safety in AI-based system architectures
Detection and mitigation of AI safety risks
Avoiding negative side effects in AI-based systems
Regulating AI-based systems: safety standards and certification
Evaluation platforms for AI safety
AI safety education and awareness
Safety and ethical issues of Generative AI
We welcome and encourage the submission of high-quality, original papers which are not simultaneously submitted for publication elsewhere. Papers should be written in English, formatted according to the Springer Verlag LNCS style in a pdf form, which can be obtained from https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelinesand not exceed 14 pages, including figures, references, etc. If you use a word file, please follow the instruction of the format, and then convert it into a PDF form and submit it at the paper submission page:
https://easychair.org/conferences/?conf=aisecurityprivacy202
All submissions will be blind-refereed and thus must be anonymous, with no author names, affiliations, acknowledgments, or obvious references. Submissions must not substantially duplicate work that any of the authors has published elsewhere or has submitted in parallel to a journal or any other conference/workshop that has proceedings. Accepted submissions may not appear in any other conference or workshop that has proceedings. Submissions not meeting these guidelines risk rejection without consideration of their merits.
If a paper is accepted, at least one author of the paper must register the workshop through this page. Without fulfilling this condition, the paper will not be in the proceedings.
We publish accepted papers which have LNAI quality in IsAI2025 proceedings in LNAI series which is different from treatment of the previous years (previously there were post-proceedings).