Turning Attacks into Protection: Social Media Privacy Protection Using Adversarial Attacks
Turning Attacks into Protection: Social Media Privacy Protection Using Adversarial Attacks
复制标题
将攻击转化为保护：使用对抗性攻击的社交媒体隐私保护
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Dinghao Wu
中科院分区：
文献类型：
--
作者：
Xiaoting Li;Lingwei Chen;Dinghao Wu
机器学习，特别是深度学习，已经成为社交媒体上属性推断攻击的最强大工具之一，这对用户的隐私和安全构成了严重威胁。在本文中，我们探索了在社交媒体中保护数据隐私的新视角，利用机器学习的脆弱性，并引入对抗性攻击来伪造潜在特征表示和误导属性推理攻击。考虑到社交媒体中的文本数据共享用户最重要的隐私，我们研究了如何精心设计文本空间对抗性攻击来混淆用户的属性，并相应地提出了文本空间对抗性攻击作为防御，或简称AaaD。具体来说，我们通过构建语义和视觉上相似的候选词来扰乱AaaD，并利用词的重要性分数作为选择概率来升级基于群体的优化，以加快对抗性文本的生成。我们在两个社交媒体数据集上评估了AaaD的性能，实验结果验证了其对推理攻击的有效性。我们的工作产生了巨大的价值，并揭示了对抗性攻击在属性混淆和隐私保护方面的适用性。
Machine learning, especially deep learning, has emerged as one of the most powerful tools for attribute inference attacks over social media, which poses serious threats to users’ privacy and security. In this paper, we explore a novel perspective of protecting data privacy in social media, where we take advantage of the vulnerability of machine learning, and introduce adversarial attacks to forge latent feature representations and mislead attribute inference attacks. Considering that text data in social media shares the most significant privacy of users, we investigate how text-space adversarial attacks can be elaborated to obfuscate users’ attributes, and accordingly present a text-space adversarial attack as defense , or AaaD for short. Specifically, we advance AaaD by constructing semantically and visually similar word candidates to perturb, and leveraging word importance scores as selection probabilities to upgrade a population-based optimization to expedite adversarial text generation. We evaluate the performance of AaaD on two social media data sets, while the experimental results validate its effectiveness against inference attacks. Our work yields great value and unveils a new insight on the applicability of adversarial attacks for attribute obfuscation and privacy protection.
DOI：
10.1109/iccv.2017.165
发表时间：
2017-03
期刊：
2017 IEEE International Conference on Computer Vision (ICCV)
影响因子：
--
作者：
Seong Joon Oh;Mario Fritz;B. Schiele
通讯作者：
Seong Joon Oh;Mario Fritz;B. Schiele
DOI：
--
发表时间：
2017-08
期刊：
--
影响因子：
--
作者：
Tianhao Wang;Jeremiah Blocki;Ninghui Li;S. Jha
通讯作者：
Tianhao Wang;Jeremiah Blocki;Ninghui Li;S. Jha
社交网络上的对抗性分类
DOI：
--
发表时间：
2018
期刊：
International Conference on Autonomous Agents and Multiagent Systems
影响因子：
--
作者：
Yu, Sixie;Vorobeychik, Yevgeniy;Alfeld, Scott
通讯作者：
Alfeld, Scott