Adversarial Attacks and Defenses for Deep Learning

Dear Colleagues,

Deep Learning (DL) is at the heart of the current rise of artificial intelligence. It is everywhere, ranging from traffic prediction, to medical diagnosis, to self-autonomous driving. However, the security vulnerability of DL algorithms to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs has been widely recognized. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in real-world problems. Hence, adversarial attack and defense techniques have attracted increasing attention from both machine learning and security communities, and have become a hot research topic in recent years.

This Special Issue encourages authors, from academia and industry, to submit new research results about adversarial attacks and defenses for deep learning. The Special Issue topics include but are not limited to the following:

• Foundations of understanding adversarial machine learning;
• Theory and algorithms for attacking with adversarial learning;
• Robustness certification and property verification techniques;
• Protection and detection techniques against black-box, white-box, and gray-box adversarial attacks;
• Defenses against training/testing attacks;
• Novel applications of adversarial learning and security.

Dr. Francisco Javier García Polo
Guest Editor

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. AI is an international peer-reviewed open access quarterly 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.

• deep learning
• adversarial attacks
• defenses