MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2024 2verdicts
UNVERDICTED 2representative citing papers
EchoAlign adjusts instances with controllable generative models to match noisy labels and selects reliable subsets, outperforming prior methods on benchmarks especially under 30% instance-dependent noise.
citing papers explorer
-
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.
-
EchoAlign: Bridging Generative and Discriminative Learning under Noisy Labels
EchoAlign adjusts instances with controllable generative models to match noisy labels and selects reliable subsets, outperforming prior methods on benchmarks especially under 30% instance-dependent noise.