The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The paper investigates privacy risks in Vision Transformer (ViT) split‑inference systems that use token reduction and token shuffling to lower computation and communication costs. It shows that even after token shuffling, transmitted token embeddings still contain enough positional information for a new attack, the Spatially Aligned Reconstruction Attack (SARA), which predicts token positions, restores spatial layout, fills missing embeddings with a masked autoencoder, and reconstructs the input image. While token reduction offers stronger protection, significant leakage remains when retained tokens preserve semantic and positional cues, and the authors propose a lightweight edge‑side defense that removes positional embeddings and adapts transformer blocks via knowledge distillation to reduce SARA’s effectiveness without harming downstream accuracy.
arXiv:2608. 04477v1 Announce Type: cross Abstract: Cloud-based language model services routinely process prompts containing sensitive information.
arXiv:2607. 02819v1 Announce Type: cross Abstract: Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers.
arXiv:2607. 00174v1 Announce Type: cross Abstract: 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 input preprocessing pipeline.
Image matching is a core component of applications such as Simultaneous Localization and Mapping (SLAM), Visual Localization, and Structure from Motion (SfM). However, the local image features central...
arXiv:2608.23012v1 Announce Type: new Abstract: Image matching is a core component of applications such as Simultaneous Localization and Mapping (SLAM), Visual Localization, and Structure from Motion...