Standard model inversion evaluation counts many adversarial false positives as successes; MLLM-based evaluation reveals consistently high false-positive rates across 27 attack setups.
Towards fine-grained visual representations by combining contrastive learning with image reconstruction and attention-weighted pooling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment
Standard model inversion evaluation counts many adversarial false positives as successes; MLLM-based evaluation reveals consistently high false-positive rates across 27 attack setups.