Related papers: Tight Auditing of Differentially Private Machine L…
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…
The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled "Federated Learning with Formal Differential Privacy Guarantees"). In…
Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters $(\epsilon,\delta)$. Choosing…
Statistical model checking is a class of sequential algorithms that can verify specifications of interest on an ensemble of cyber-physical systems (e.g., whether 99% of cars from a batch meet a requirement on their energy efficiency). These…
Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data…
Fairness auditing of AI systems can identify and quantify biases. However, traditional auditing using real-world data raises security and privacy concerns. It exposes auditors to security risks as they become custodians of sensitive…
Differential Privacy has become a widely popular method for data protection in machine learning, especially since it allows formulating strict mathematical privacy guarantees. This survey provides an overview of the state-of-the-art of…
Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy…
Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…
We present new auditors to assess Differential Privacy (DP) of an algorithm based on output samples. Such empirical auditors are common to check for algorithmic correctness and implementation bugs. Most existing auditors are batch-based or…
The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is designed to prevent the reconstruction of sensitive information.…
Recent methods for auditing the privacy of machine learning algorithms have improved computational efficiency by simultaneously intervening on multiple training examples in a single training run. Steinke et al. (2024) prove that one-run…
Machine learning models can be trained with formal privacy guarantees via differentially private optimizers such as DP-SGD. In this work, we focus on a threat model where the adversary has access only to the final model, with no visibility…
Ratio statistics--such as relative risk and odds ratios--play a central role in hypothesis testing, model evaluation, and decision-making across many areas of machine learning, including causal inference and fairness analysis. However,…
Differential privacy offers formal quantitative guarantees for algorithms over datasets, but it assumes attackers that know and can influence all but one record in the database. This assumption often vastly overapproximates the attackers'…
This work proposes an algorithmic method to verify differential privacy for estimation mechanisms with performance guarantees. Differential privacy makes it hard to distinguish outputs of a mechanism produced by adjacent inputs. While…
A surge in data-driven applications enhances everyday life but also raises serious concerns about private information leakage. Hence many privacy auditing tools are emerging for checking if the data sanitization performed meets the privacy…
In this paper we propose new methods to statistically assess $f$-Differential Privacy ($f$-DP), a recent refinement of differential privacy (DP) that remedies certain weaknesses of standard DP (including tightness under algorithmic…
We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realistic privacy attacks.…
In modern settings of data analysis, we may be running our algorithms on datasets that are sensitive in nature. However, classical machine learning and statistical algorithms were not designed with these risks in mind, and it has been…