Related papers: A Note On Interpreting Canary Exposure
Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…
Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…
Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we…
As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to affected individuals. While such recourses can be immensely…
The right to be forgotten states that a data owner has the right to erase their data from an entity storing it. In the context of machine learning (ML), the right to be forgotten requires an ML model owner to remove the data owner's data…
Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of…
Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to…
Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…
Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning…
The performance of differentially private machine learning can be boosted significantly by leveraging the transfer learning capabilities of non-private models pretrained on large public datasets. We critically review this approach. We…
Interpretable predictions, where it is clear why a machine learning model has made a particular decision, can compromise privacy by revealing the characteristics of individual data points. This raises the central question addressed in this…
Over the past few years, providers such as Google, Microsoft, and Amazon have started to provide customers with access to software interfaces allowing them to easily embed machine learning tasks into their applications. Overall,…
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…
Differential Privacy can provide provable privacy guarantees for training data in machine learning. However, the presence of proofs does not preclude the presence of errors. Inspired by recent advances in auditing which have been used for…
The successful deployment of artificial intelligence (AI) in many domains from healthcare to hiring requires their responsible use, particularly in model explanations and privacy. Explainable artificial intelligence (XAI) provides more…
We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward evaluating privacy loss through poisoning attacks or…
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…
Current techniques for privacy auditing of large language models (LLMs) have limited efficacy -- they rely on basic approaches to generate canaries which leads to weak membership inference attacks that in turn give loose lower bounds on the…
The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…