VVSec: Securing Volumetric Video Streaming via Benign Use of Adversarial Perturbation

VVSec: Securing Volumetric Video Streaming via Benign Use of Adversarial Perturbation
复制标题

VVSec:通过善意地使用对抗性扰动来保护体积视频流

DOI:
10.1145/3394171.3413639
复制
发表时间:
2020
期刊:
ACM International Conference on Multimedia
影响因子:
--
通讯作者:
Wei, Sheng
Wei, Sheng
中科院分区:
--
文献类型:
--
作者:
Tang, Zhongze;Feng, Xianglong;Xie, Yi;Phan, Huy;Guo, Tian;Yuan, Bo;Wei, Sheng

文献摘要

参考文献

相似文献

随着消费类VR/AR设备以及相关多媒体和图形研究的快速发展,体视频(VV)流媒体最近引起了越来越多的兴趣。虽然容量视频流的资源和性能的挑战已经积极调查的多媒体社区,潜在的安全和隐私问题,这种新型的多媒体还没有被研究。我们第一次确定了一个有效的威胁模型,提取三维人脸模型从体积视频和妥协的脸ID为基础的认证,以抵御这种攻击,我们开发了一种新的体积视频安全机制,即VVSec,它使良性使用对抗扰动混淆的安全性和隐私敏感的三维人脸模型。这种混淆确保了3D模型不能被利用来绕过基于深度学习的人脸认证。同时,注入的扰动不会被终端用户感知,从而保持了体积视频流传输中的原始体验质量。我们使用两个数据集来评估VVSec,包括从经验体积视频和公共RGB-D人脸图像数据集提取的一组帧。我们的评估结果表明,所提出的攻击和防御机制在体积视频流的有效性。
Volumetric video (VV) streaming has drawn an increasing amount of interests recently with the rapid advancements in consumer VR/AR devices and the relevant multimedia and graphics research. While the resource and performance challenges in volumetric video streaming have been actively investigated by the multimedia community, the potential security and privacy concerns with this new type of multimedia have not been studied. We for the first time identify an effective threat model that extracts 3D face models from volumetric videos and compromises face ID-based authentications To defend against such attack, we develop a novel volumetric video security mechanism, namely VVSec, which makes benign use of adversarial perturbations to obfuscate the security and privacy-sensitive 3D face models. Such obfuscation ensures that the 3D models cannot be exploited to bypass deep learning-based face authentications. Meanwhile, the injected perturbations are not perceivable by the end-users, maintaining the original quality of experience in volumetric video streaming. We evaluate VVSec using two datasets, including a set of frames extracted from an empirical volumetric video and a public RGB-D face image dataset. Our evaluation results demonstrate the effectiveness of both the proposed attack and defense mechanisms in volumetric video streaming.
计算机视觉深度学习
DOI: --
发表时间: 2018
期刊:
影响因子: --
作者:
Rajalingappaa Shanmugamani
通讯作者: Rajalingappaa Shanmugamani
DOI: 10.1109/jetcas.2018.2885981
发表时间: 2019-03-01
影响因子: 4.6
作者:
Schwarz, Sebastian;Preda, Marius;Zakharchenko, Vladyslav
通讯作者: Zakharchenko, Vladyslav
DOI: 10.1109/sp40000.2020.00089
发表时间: 2020-05
期刊: 2020 IEEE Symposium on Security and Privacy (SP)
影响因子: --
作者:
Jo Van Bulck;D. Moghimi;Michael Schwarz;Moritz Lipp;Marina Minkin;Daniel Genkin;Y. Yarom;B. Sunar-B.-Su
通讯作者: Jo Van Bulck;D. Moghimi;Michael Schwarz;Moritz Lipp;Marina Minkin;Daniel Genkin;Y. Yarom;B. Sunar-B.-Su
CAG:实时低成本增强鲁棒性高可转移性内容感知对抗攻击生成器
DOI: --
发表时间: 2019
期刊: AAAI Conference on Artificial Intelligence
影响因子: --
作者:
Huy Phan;Yi Xie;Siyu Liao;Jie Chen;Bo Yuan
通讯作者: Bo Yuan
DOI: 10.1609/aaai.v33i01.33018481
发表时间: 2019-07
期刊: --
影响因子: --
作者:
Wenlong Huang;B. Lai;Weijian Xu;Z. Tu
通讯作者: Wenlong Huang;B. Lai;Weijian Xu;Z. Tu