activity
20232026
most citedEfficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

2 citations · 3 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Steal the Patch Size: Adversarially Manipulate Vision-Language Models

Kai Hu, Akash Bharadwaj, Weichen Yu +1

We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and in…