Areas of interest include (but not limited to):

• Adversarial/poisoning attacks against deep learning tasks
• Defenses to improve deep learning system robustness
• Privacy-preserving deep learning systems and protocols
• Secure computation based solutions for deep learning training and inference
• Privacy inference attacks against deep learning systems, e.g., membership inference, model extraction, model inversion
• Intersection among fairness, privacy, robustness, explainability, accountability, and environmental wellbeings in deep learning systems
• Trustworthy deep learning systems for domain specific applications, e.g., energy, medical AI, smart manufacturing, etc.
• Secure federated systems for decentralised deep learning
• Security and privacy in on-device deep learning systems and applications

Position papers describing the work in progress are also welcome.

Submission Instructions

Submitted papers must not substantially overlap papers that have been published or that are simultaneously submitted to a journal or a conference with proceedings. All submissions should be appropriately anonymized and a DOUBLE-BLIND REVIEW policy will be applied during the review process. Submissions must be in double-column ACM SIG Proceedings format, and should not exceed the following page limit.

• Full-Length Paper = 12 Page Limit + up to 2 extra pages for appendices only
• Short Paper = 6 Page Limit + up to 2 extra pages for appendices only

Only pdf files will be accepted. Authors of accepted papers must guarantee that their papers will be presented at the workshop. At least one author of the paper must be registered at the appropriate conference rate. Accepted papers will be published in the ACM Digital Library. This symposium will grant a Best Paper Award.

Submission site is now open.

Submit Your Paper Here

Important Dates

Submission Deadline: Feb 15th, 2023Feb 28th, 2023 (no extension)

Notification Due: March 31st, 2023

Camera Ready Version Due: April 24th, 2023

Conference Date: July 10th, 2023