Mirage auditing reveals that VFL unlearning methods passing output-level checks still retain substantial class structure in representations across multiple datasets and baselines.
In: 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning
Mirage auditing reveals that VFL unlearning methods passing output-level checks still retain substantial class structure in representations across multiple datasets and baselines.