A side-channel attack infers ViT patch size from periodic accuracy collapses on aligned grid images, enabling preprocessing-aware transfer attacks on VLMs.
Transferable adversarial attacks on black-box vision-language models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
First study of image prompt reconstruction attacks on distributed MLLM inference, proposing MPAA for pixel-level and IEDA for semantic reconstruction with 100% embedding extraction accuracy on four model families.
MCRMO-Attack raises universal targeted attack success rates on unseen images by 23.7% on GPT-4o and 19.9% on Gemini-2.0 over prior universal baselines through stabilized supervision and meta-optimization.
Attacking only the top 20% high-entropy token positions in vision-language models causes comparable semantic damage and more harmful outputs than global attacks, and these vulnerable tokens transfer across model architectures.
FRA-Attack uses high-pass DCT feature alignment and frequency-domain gradient regularization to boost adversarial transferability across 15 MLLMs from 7 vendors.
Adversarial examples enable AI authority laundering by causing production VLMs to give authoritative but wrong responses on subtly perturbed images, with success rates of 22-100% using decade-old attack methods.
citing papers explorer
-
Steal the Patch Size: Adversarially Manipulate Vision-Language Models
A side-channel attack infers ViT patch size from periodic accuracy collapses on aligned grid images, enabling preprocessing-aware transfer attacks on VLMs.
-
Image Prompt Reconstruction Attacks on Distributed MLLM Inference Frameworks
First study of image prompt reconstruction attacks on distributed MLLM inference, proposing MPAA for pixel-level and IEDA for semantic reconstruction with 100% embedding extraction accuracy on four model families.
-
Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization
MCRMO-Attack raises universal targeted attack success rates on unseen images by 23.7% on GPT-4o and 19.9% on Gemini-2.0 over prior universal baselines through stabilized supervision and meta-optimization.
-
High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models
Attacking only the top 20% high-entropy token positions in vision-language models causes comparable semantic damage and more harmful outputs than global attacks, and these vulnerable tokens transfer across model architectures.
-
Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
FRA-Attack uses high-pass DCT feature alignment and frequency-domain gradient regularization to boost adversarial transferability across 15 MLLMs from 7 vendors.
-
Laundering AI Authority with Adversarial Examples
Adversarial examples enable AI authority laundering by causing production VLMs to give authoritative but wrong responses on subtly perturbed images, with success rates of 22-100% using decade-old attack methods.