paper-with-me

홈 › Papers

Unauthorized AI cannot Recognize Me: Reversible Adversarial Example

2018-11-01 · Jiayang Liu, Weiming Zhang, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma

In this study, we propose a new methodology to control how user's data is recognized and used by AI via exploiting the properties of adversarial examples. For this purpose, we propose reversible adversarial example (RAE), a new type of adversarial example. A remarkable feature of RAE is that the image can be correctly recognized and used by the AI model specified by the user because the authorized AI can recover the original image from the RAE exactly by eliminating adversarial perturbation. On the other hand, other unauthorized AI models cannot recognize it correctly because it functions as an adversarial example. Moreover, RAE can be considered as one type of encryption to computer vision since reversibility guarantees the decryption. To realize RAE, we combine three technologies, adversarial example, reversible data hiding for exact recovery of adversarial perturbation, and encryption for selective control of AIs who can remove adversarial perturbation. Experimental results show that the proposed method can achieve comparable attack ability with the corresponding adversarial attack method and similar visual quality with the original image, including white-box attacks and black-box attacks.

📄 PDF Abstract BibTeX arXiv:1811.00189

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackBIG-bench Machine LearningGeneral ClassificationImage ClassificationSpeech Recognition

Similar Papers 제목 키워드 기반

Reversible Adversarial Attack based on Reversible Image Transformation

2019-11-06 · Zhaoxia Yin, Hua Wang, Li Chen, Jie Wang 외

In order to prevent illegal or unauthorized access of image data such as human faces and ensure legitimate users can use authorization-protected data, reversible adversarial attack technique is rise. Reversible adversari…

Adversarial AttackImage Restoration

Reversible Attack based on Local Visual Adversarial Perturbation

2021-10-06 · Li Chen, Shaowei Zhu, Zhaoxia Yin

Adding perturbations to images can mislead classification models to produce incorrect results. Recently, researchers exploited adversarial perturbations to protect image privacy from retrieval by intelligent models. Howe…

Adversarial AttackAutonomous DrivingFace RecognitionRetrieval

DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection

2025-05-11 · Xia Du, JiaJie Zhu, Jizhe Zhou, Chi-Man Pun 외

In the field of digital security, Reversible Adversarial Examples (RAE) combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malici…

RAEDiff: Denoising Diffusion Probabilistic Models Based Reversible Adversarial Examples Self-Generation and Self-Recovery

2023-10-25 · Fan Xing, Xiaoyi Zhou, Xuefeng Fan, Zhuo Tian 외

Collected and annotated datasets, which are obtained through extensive efforts, are effective for training Deep Neural Network (DNN) models. However, these datasets are susceptible to be misused by unauthorized users, re…

Denoising

RAEncoder: A Label-Free Reversible Adversarial Examples Encoder for Dataset Intellectual Property Protection

2025-01-01 · CVPR 2025 1 · Fan Xing, Zhuo Tian, Xuefeng Fan, Xiaoyi Zhou

Reversible Adversarial Examples (RAE) are designed to protect the intellectual property of datasets. Such examples can function as imperceptible adversarial examples to erode the model performance of unauthorized use…

Self-Supervised Learning