Related papers: Trade-offs and Guarantees of Adversarial Represent…

Machine learning is increasingly used in the most diverse applications and domains, whether in healthcare, to predict pathologies, or in the financial sector to detect fraud. One of the linchpins for efficiency and accuracy in machine…

Preserving privacy of continuous and/or high-dimensional data such as images, videos and audios, can be challenging with syntactic anonymization methods which are designed for discrete attributes. Differential privacy, which provides a more…

The integration of fairness and privacy in centralized data-driven applications is critical, especially as these systems increasingly influence sectors with significant societal impact. Current methods rarely address privacy, fairness, and…

We introduce a tunable measure for information leakage called maximal alpha-leakage. This measure quantifies the maximal gain of an adversary in inferring any (potentially random) function of a dataset from a release of the data. The…

Recently, it has been shown that Machine Learning models can leak sensitive information about their training data. This information leakage is exposed through membership and attribute inference attacks. Although many attack strategies have…

Recent advances in natural language processing have enabled powerful privacy-invasive authorship attribution. To counter authorship attribution, researchers have proposed a variety of rule-based and learning-based text obfuscation…

Personal photos of individuals when shared online, apart from exhibiting a myriad of memorable details, also reveals a wide range of private information and potentially entails privacy risks (e.g., online harassment, tracking). To mitigate…

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…

We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data. In particular, we face the case where some attributes (bias) of the data, if learned by the model, can severely…

In this paper, we first introduce the notion of channel leakage as the minimum mutual information between the channel input and channel output. As its name indicates, channel leakage quantifies the minimum information leakage to the…

As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and…

We propose learning discrete structured representations from unlabeled data by maximizing the mutual information between a structured latent variable and a target variable. Calculating mutual information is intractable in this setting. Our…

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…

While users claim to be concerned about privacy, often they do little to protect their privacy in their online actions. One prominent explanation for this "privacy paradox" is that when an individual shares her data, it is not just her…

Over the past decade, side-channels have proven to be significant and practical threats to modern computing systems. Recent attacks have all exploited the underlying shared hardware. While practical, mounting such a complicated attack is…

We study an information theoretic privacy mechanism design problem for two scenarios where the private data is either observable or hidden. In each scenario, we first consider bounded mutual information as privacy leakage criterion, then we…

Many of the successes of machine learning are based on minimizing an averaged loss function. However, it is well-known that this paradigm suffers from robustness issues that hinder its applicability in safety-critical domains. These issues…

We study the extent to which standard machine learning algorithms rely on exchangeability and independence of data by introducing a monotone adversarial corruption model. In this model, an adversary, upon looking at a "clean" i.i.d.…

We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arbitrary privacy…

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…