arXiv Machine Learning
A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
Aug 31
A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets
Deep learning-based side-channel analysis has historically focused on single-byte targets and manually cropped traces, which risks discarding exploitable leakage. While recent work has proposed specia...
arXiv AI
Sep 2
Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling
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 Machine Learning
Jun 4
Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks
arXiv:2606. 04317v1 Announce Type: cross Abstract: Deep neural networks are increasingly deployed across heterogeneous and partially untrusted environments, where models are distributed through cloud storage, CI/CD pipelines, containerized services, and edge execution platforms.
Hugging Face Trending Papers
Sep 1
Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling
Vision Transformers (ViTs) are increasingly used in split-inference systems, where edge devices transmit intermediate token representations to a remote cloud. In this setting, token reduction lowers c...
arXiv Machine Learning
Jul 9
InferNet: Exploiting Aggregate GPU Profiles as Side-Channel for DNN Architecture Inference
arXiv:2304. 03388v2 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have become ubiquitous for their ability to solve problems across various domains, including computer vision, natural language processing, and speech recognition.
arXiv Machine Learning
Jul 2
Steal the Patch Size: Adversarially Manipulate Vision-Language Models
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.