.png){kind=icon}
返回
A destructive active defense algorithm for deepfake face images
.png){kind=icon}
OA
AI
DOI：10.7717/peerj-cs.2356.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The harm caused by deepfake face images is increasing. To proactively defend against this threat, this paper innovatively proposes a destructive active defense algorithm for deepfake face images (DADFI). This algorithm adds slight perturbations to the original face images to generate adversarial samples. These perturbations are imperceptible to the human eye but cause significant distortions in the outputs of mainstream deepfake models. Firstly, the algorithm generates adversarial samples that maintain high visual fidelity and authenticity. Secondly, in a black-box scenario, the adversarial samples are used to attack deepfake models to enhance their offensive capabilities. Finally, destructive attack experiments were conducted on the mainstream face datasets CASIAFaceV5 and CelebA. The results demonstrate that the proposed DADFI algorithm not only improves the generation speed of adversarial samples but also increases the success rate of active defense. This achievement can effectively reduce the harm caused by deepfake face images.
Keyword:
Deep fake
Face images
Active defense
Adversarial samples
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
2.5
论文数:
3.4K
被引数:
6.9K
机构
引用论文
Fighting fake reviews: Authenticated anonymous reviews using identity verification打击虚假评论: 使用身份验证进行身份验证的匿名评论
PREAI
分享收藏ATS-O2A: A state-based adversarial attack strategy on deep reinforcement learningATS-O2A: 基于状态的深度强化学习对抗性攻击策略.png)
COMPUTERS & SECURITY
COMPUTERS & SECURITYIF5.4
PREAI
分享收藏Mastering Deepfake Detection: A Cutting-edge Approach to Distinguish GAN and Diffusion-model Images掌握Deepfake检测: 区分GAN和扩散模型图像的尖端方法
OAAI
OAAI分享收藏Generative Adversarial Networks in Time Series: A Systematic Literature Review时间序列中的生成对抗网络: 系统文献综述OAAI
OAAI分享收藏A multi-objective memetic algorithm for automatic adversarial attack optimization design面向自动对抗攻击优化设计的多目标模因算法NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容