{AttriGuard}: A practical defense against attribute inference attacks via adversarial machine learning

J Jia, NZ Gong - 27th USENIX Security Symposium (USENIX Security …, 2018 - usenix.org
Users in various web and mobile applications are vulnerable to attribute inference attacks, in
which an attacker leverages a machine learning classifier to infer a target user's private …

You are who you know and how you behave: Attribute inference attacks via users' social friends and behaviors

NZ Gong, B Liu - 25th USENIX Security Symposium (USENIX Security …, 2016 - usenix.org
We propose new privacy attacks to infer attributes (eg, locations, occupations, and interests)
of online social network users. Our attacks leverage seemingly innocent user information …

Privacy inference attack against users in online social networks: a literature review

Y Piao, K Ye, X Cui - IEEE Access, 2021 - ieeexplore.ieee.org
With the rapid development of social networks, users pay more and more attention to the
protection of personal information. However, the transmission of users' personal information …

Privacy aspects of recommender systems

A Friedman, BP Knijnenburg, K Vanhecke… - Recommender systems …, 2015 - Springer
The popularity of online recommender systems has soared; they are deployed in numerous
websites and gather tremendous amounts of user data that are necessary for …

Defending against machine learning based inference attacks via adversarial examples: Opportunities and challenges

J Jia, NZ Gong - Adaptive autonomous secure cyber systems, 2020 - Springer
As machine learning (ML) becomes more and more powerful and easily accessible,
attackers increasingly leverage ML to perform automated large-scale inference attacks in …

[HTML][HTML] Towards user-oriented privacy for recommender system data: A personalization-based approach to gender obfuscation for user profiles

M Slokom, A Hanjalic, M Larson - Information Processing & Management, 2021 - Elsevier
In this paper, we propose a new privacy solution for the data used to train a recommender
system, ie, the user–item matrix. The user–item matrix contains implicit information, which …

PrivStream: A privacy-preserving inference framework on IoT streaming data at the edge

D Wang, J Ren, Z Wang, Y Zhang, XS Shen - Information Fusion, 2022 - Elsevier
Edge computing combining with artificial intelligence (AI) has enabled the timely processing
and analysis of streaming data produced by IoT intelligent applications. However, it causes …

Attribute inference attacks in online multiplayer video games: A case study on Dota2

PP Tricomi, L Facciolo, G Apruzzese… - Proceedings of the …, 2023 - dl.acm.org
Did you know that over 70 million of Dota2 players have their in-game data freely
accessible? What if such data is used in malicious ways? This paper is the first to investigate …

Incognito: A method for obfuscating web data

R Masood, D Vatsalan, M Ikram… - … of the 2018 world wide web …, 2018 - dl.acm.org
Users leave a trail of their personal data, interests, and intents while surfing or sharing
information on the Web. Web data could therefore reveal some private/sensitive information …

Preventing disclosure of personal data in IoT networks

I Torre, G Adorni, F Koceva… - 2016 12th International …, 2016 - ieeexplore.ieee.org
Sharing data among applications is a growing phenomenon. With the IoT, this phenomenon
becomes more significant. As already studied in social networks, data sharing has the …