Attacking Compressed Vision Transformers

2022-09-28 · Swapnil Parekh, Devansh Shah, Pratyush Shukla

Vision Transformers are increasingly embedded in industrial systems due to their superior performance, but their memory and power requirements make deploying them to edge devices a challenging task. Hence, model compression techniques are now widely used to deploy models on edge devices as they decrease the resource requirements and make model inference very fast and efficient. But their reliability and robustness from a security perspective is another major issue in safety-critical applications. Adversarial attacks are like optical illusions for ML algorithms and they can severely impact the accuracy and reliability of models. In this work we investigate the transferability of adversarial samples across the SOTA Vision Transformer models across 3 SOTA compressed versions and infer the effects different compression techniques have on adversarial attacks.

📄 PDF Abstract BibTeX arXiv:2209.13785

Code (1)

swapnildreams100/attacking_compressed_vits 공식 구현 pytorch

Tasks

Model Compression

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Residual Connection 설명 없음

Multi-Head Attention 설명 없음

Transformers from Compressed Representations

2025-10-26 · Juan C. Leon Alcazar, Mattia Soldan, Mohammad Saatialsoruji, Alejandro Pardo 외 arxiv

Compressed file formats are the corner stone of efficient data storage and transmission, yet their potential for representation learning remains largely underexplored. We introduce TEMPEST (TransformErs froM comPressed r…

Representation Learning

Adversarial Attention Perturbations for Large Object Detection Transformers

2025-08-05 · Zachary Yahn, Selim Furkan Tekin, Fatih Ilhan, Sihao Hu 외 arxiv

Adversarial perturbations are useful tools for exposing vulnerabilities in neural networks. Existing adversarial perturbation methods for object detection are either limited to attacking CNN-based detectors or weak again…

Object Detection

Diversity-Guided MLP Reduction for Efficient Large Vision Transformers

2025-06-10 · Chengchao Shen, Hourun Zhu, Gongfan Fang, Jianxin Wang 외

Transformer models achieve excellent scaling property, where the performance is improved with the increment of model capacity. However, large-scale model parameters lead to an unaffordable cost of computing and memory. W…

Diversity

Towards End-to-End Image Compression and Analysis with Transformers

2021-12-17 · Yuanchao Bai, Xu Yang, Xianming Liu, Junjun Jiang 외

We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model …

Classification image-classification Image Classification Image Compression+2

Full Contextual Attention for Multi-resolution Transformers in Semantic Segmentation

2022-12-15 · Loic Themyr, Clement Rambour, Nicolas Thome, Toby Collins 외

Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens. Multi-resoluti…

Semantic Segmentation