A temperature-perturbed black-box attack infers video training membership in VideoLLMs with 0.68 AUC by exploiting sharper generation behavior on member samples.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Mirage auditing framework reveals that VFL unlearning methods passing output-level certification retain substantial class structure in representations, with no method achieving high utility plus both output and representation forgetting, plus class-sample asymmetry in residual traces.
Fully connected neural network with randomized loss synthesizes real-world tabular data distributions from Gaussian noise faster than state-of-the-art deep generative models.
citing papers explorer
-
Membership Inference Attacks Against Video Large Language Models
A temperature-perturbed black-box attack infers video training membership in VideoLLMs with 0.68 AUC by exploiting sharper generation behavior on member samples.
-
Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning
Mirage auditing framework reveals that VFL unlearning methods passing output-level certification retain substantial class structure in representations, with no method achieving high utility plus both output and representation forgetting, plus class-sample asymmetry in residual traces.
-
Synthesizing real-world distributions from high-dimensional Gaussian Noise with Fully Connected Neural Network
Fully connected neural network with randomized loss synthesizes real-world tabular data distributions from Gaussian noise faster than state-of-the-art deep generative models.