Areas of interest include (but not limited to):

• Robust Deep Learning Systems: Attacks against deep learning systems and corresponding defence
• Privacy-preserving Deep Learning Systems and Protocols
• Privacy inference attacks against deep learning systems, e.g., membership/property inference, model extraction, model inversion.
• Fairness and Equity in Decision Making and intersection among Fairness, Privacy, Robustness, Explainability, Accountability, etc
• Machine Unlearning and Verification Mechanism
• Secure federated systems for decentralised deep learning
• Transparency and Interpretability of AI
• Privacy-preserving Graph Neuron Networks
• Trustworthy deep learning systems for domain specific applications, e.g., energy, medical AI, smart manufacturing, 5G and 6G networks
• Security and privacy in on-device deep learning systems and applications
• Security and Privacy in LLM-integrated systems, e.g, information leakage, prompt injection, prompt privacy

Submission Instructions

Paper submission site: (via HotCRP, TBA)

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 (see here) and should not exceed 12 pages, including references and appendices.

Position papers describing the work in progress are also welcome. 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.

Important Dates (Two Cycles)