Mirage auditing reveals that VFL unlearning methods passing output-level checks still retain substantial class structure in representations across multiple datasets and baselines.
In: 2021 IEEE symposium on security and privacy (SP)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CSC identifies backdoored samples via early-epoch latent clustering and conceals them by relabeling to a virtual class, driving attack success rates near zero on benchmarks with little clean accuracy loss.
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.
-
CSC: Turning the Adversary's Poison against Itself
CSC identifies backdoored samples via early-epoch latent clustering and conceals them by relabeling to a virtual class, driving attack success rates near zero on benchmarks with little clean accuracy loss.