Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models

A Salem, Y Zhang, M Humbert, P Berrang… - arxiv preprint arxiv …, 2018 - arxiv.org
Machine learning (ML) has become a core component of many real-world applications and
training data is a key factor that drives current progress. This huge success has led Internet …

Memguard: Defending against black-box membership inference attacks via adversarial examples

J Jia, A Salem, M Backes, Y Zhang… - Proceedings of the 2019 …, 2019 - dl.acm.org
In a membership inference attack, an attacker aims to infer whether a data sample is in a
target classifier's training dataset or not. Specifically, given a black-box access to the target …

Dynamic backdoor attacks against machine learning models

A Salem, R Wen, M Backes, S Ma… - 2022 IEEE 7th …, 2022 - ieeexplore.ieee.org
Machine learning (ML) has made tremendous progress during the past decade and is being
adopted in various critical real-world applications. However, recent research has shown that …

{Updates-Leak}: Data set inference and reconstruction attacks in online learning

A Salem, A Bhattacharya, M Backes, M Fritz… - 29th USENIX security …, 2020 - usenix.org
Machine learning (ML) has progressed rapidly during the past decade and the major factor
that drives such development is the unprecedented large-scale data. As data generation is a …

Privacy risks of general-purpose language models

X Pan, M Zhang, S Ji, M Yang - 2020 IEEE Symposium on …, 2020 - ieeexplore.ieee.org
Recently, a new paradigm of building general-purpose language models (eg, Google's Bert
and OpenAI's GPT-2) in Natural Language Processing (NLP) for text feature extraction, a …

Retagnn: Relational temporal attentive graph neural networks for holistic sequential recommendation

C Hsu, CT Li - Proceedings of the web conference 2021, 2021 - dl.acm.org
Sequential recommendation (SR) is to accurately recommend a list of items for a user based
on her current accessed ones. While new-coming users continuously arrive in the real world …

Fairsr: Fairness-aware sequential recommendation through multi-task learning with preference graph embeddings

CT Li, C Hsu, Y Zhang - ACM Transactions on Intelligent Systems and …, 2022 - dl.acm.org
Sequential recommendation (SR) learns from the temporal dynamics of user-item
interactions to predict the next ones. Fairness-aware recommendation mitigates a variety of …

Mlcapsule: Guarded offline deployment of machine learning as a service

L Hanzlik, Y Zhang, K Grosse… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract Machine Learning as a Service (MLaaS) is a popular and convenient way to access
a trained machine learning (ML) model trough an API. However, if the user's input is …

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 …

SocInf: Membership inference attacks on social media health data with machine learning

G Liu, C Wang, K Peng, H Huang, Y Li… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Social media networks have shown rapid growth in the past, and massive social data are
generated which can reveal behavior or emotion propensities of users. Numerous social …