Author

M. Aliakbarpour

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2025

Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness

This work proposes a principled, attack-agnostic approach that uses mutual information to measure what the final model reveals about a datapoint's training membership and shows that this final-model disclosure is upper bounded by the sum of per-iteration gradient disclosures.

S. Abdelghafar, M. Aliakbarpour, Christopher Jermaine · 0 citations