paper-with-me

Papers

One-Index Vector Quantization Based Adversarial Attack on Image Classification

2024-09-02 · Haiju Fan, Xiaona Qin, Shuang Chen, Hubert P. H. Shum, Ming Li

To improve storage and transmission, images are generally compressed. Vector quantization (VQ) is a popular compression method as it has a high compression ratio that suppresses other compression techniques. Despite this, existing adversarial attack methods on image classification are mostly performed in the pixel domain with few exceptions in the compressed domain, making them less applicable in real-world scenarios. In this paper, we propose a novel one-index attack method in the VQ domain to generate adversarial images by a differential evolution algorithm, successfully resulting in image misclassification in victim models. The one-index attack method modifies a single index in the compressed data stream so that the decompressed image is misclassified. It only needs to modify a single VQ index to realize an attack, which limits the number of perturbed indexes. The proposed method belongs to a semi-black-box attack, which is more in line with the actual attack scenario. We apply our method to attack three popular image classification models, i.e., Resnet, NIN, and VGG16. On average, 55.9% and 77.4% of the images in CIFAR-10 and Fashion MNIST, respectively, are successfully attacked, with a high level of misclassification confidence and a low level of image perturbation.

📄 PDF Abstract BibTeX arXiv:2409.01282

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attackimage-classificationImage ClassificationQuantization

Similar Papers 제목 키워드 기반

Robustness of Generalized Learning Vector Quantization Models against Adversarial Attacks

2019-02-01 · Sascha Saralajew, Lars Holdijk, Maike Rees, Thomas Villmann

Adversarial attacks and the development of (deep) neural networks robust against them are currently two widely researched topics. The robustness of Learning Vector Quantization (LVQ) models against adversarial attacks ha…

Quantization

Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security

2025-11-20 · Wei Zhao, Zhe Li, Yige Li, Jun Sun arxiv

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs despite robust textual safety mechanisms…

Multimodal Reasoning

VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise

2024-06-05 · Zhixun He, Mukesh Singhal

Deep Neural Networks (DNN) have become a promising paradigm when developing Artificial Intelligence (AI) and Machine Learning (ML) applications. However, DNN applications are vulnerable to fake data that are crafted with…

Adversarial AttackQuantizationRepresentation Learning

Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization

2024-10-04 · Tung M. Luu, Thanh Nguyen, Tee Joshua Tian Jin, Sungwoon Kim 외

Recent studies reveal that well-performing reinforcement learning (RL) agents in training often lack resilience against adversarial perturbations during deployment. This highlights the importance of building a robust age…

Deep Reinforcement LearningQuantizationreinforcement-learningReinforcement Learning+1

Adversarial Defenses via Vector Quantization

2023-05-23 · Zhiyi Dong, Yongyi Mao

Building upon Randomized Discretization, we develop two novel adversarial defenses against white-box PGD attacks, utilizing vector quantization in higher dimensional spaces. These methods, termed pRD and swRD, not only o…

Quantization