Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models
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 …
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
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 …
target classifier's training dataset or not. Specifically, given a black-box access to the target …
Dynamic backdoor attacks against machine learning models
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 …
adopted in various critical real-world applications. However, recent research has shown that …
{Updates-Leak}: Data set inference and reconstruction attacks in online learning
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 …
that drives such development is the unprecedented large-scale data. As data generation is a …
Privacy risks of general-purpose language models
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 …
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 …
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
Sequential recommendation (SR) learns from the temporal dynamics of user-item
interactions to predict the next ones. Fairness-aware recommendation mitigates a variety of …
interactions to predict the next ones. Fairness-aware recommendation mitigates a variety of …
Mlcapsule: Guarded offline deployment of machine learning as a service
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 …
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
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 …
protection of personal information. However, the transmission of users' personal information …
SocInf: Membership inference attacks on social media health data with machine learning
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 …
generated which can reveal behavior or emotion propensities of users. Numerous social …