Related papers: On the Privacy Risks of Algorithmic Recourse
Membership inference attack (MIA) has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's…
Transfer learning is a useful machine learning framework that allows one to build task-specific models (student models) without significantly incurring training costs using a single powerful model (teacher model) pre-trained with a large…
Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…
Counterfactuals operationalised through algorithmic recourse have become a powerful tool to make artificial intelligence systems explainable. Conceptually, given an individual classified as y -- the factual -- we seek actions such that…
Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy concerns, especially…
Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task.…
Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…
Today, computer systems hold large amounts of personal data. Yet while such an abundance of data allows breakthroughs in artificial intelligence, and especially machine learning (ML), its existence can be a threat to user privacy, and it…
We propose a general statistical inference framework to capture the privacy threat incurred by a user that releases data to a passive but curious adversary, given utility constraints. We show that applying this general framework to the…
Recently issued data privacy regulations like GDPR (General Data Protection Regulation) grant individuals the right to be forgotten. In the context of machine learning, this requires a model to forget about a training data sample if…
Recommendation is one of the critical applications that helps users find information relevant to their interests. However, a malicious attacker can infer users' private information via recommendations. Prior work obfuscates user-item data…
Private regression has received attention from both database and security communities. Recent work by Fredrikson et al. (USENIX Security 2014) analyzed the functional mechanism (Zhang et al. VLDB 2012) for training linear regression models…
The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…
Recent attacks on Machine Learning (ML) models such as evasion attacks with adversarial examples and models stealing through extraction attacks pose several security and privacy threats. Prior work proposes to use adversarial training to…
Privacy auditing provides empirical lower bounds on the differential privacy parameters of learning algorithms. Existing methods, however, require interventional access to the training pipeline, either to retrain multiple times or to…
Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator…
Empirical defenses for machine learning privacy forgo the provable guarantees of differential privacy in the hope of achieving higher utility while resisting realistic adversaries. We identify severe pitfalls in existing empirical privacy…
In a biometric authentication or identification system, the matcher compares a stored and a fresh template to determine whether there is a match. This assessment is based on both a similarity score and a predefined threshold. For better…
As machine learning models are increasingly being employed to make consequential decisions in real-world settings, it becomes critical to ensure that individuals who are adversely impacted (e.g., loan denied) by the predictions of these…
The success of deep neural networks has driven numerous research studies and applications from Euclidean to non-Euclidean data. However, there are increasing concerns about privacy leakage, as these networks rely on processing private data.…