Related papers: Auditing without Leaks Despite Curiosity
Secure aggregation is concerned with the task of securely uploading the inputs of multiple users to an aggregation server without letting the server know the inputs beyond their summation. It finds broad applications in distributed machine…
Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…
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…
Machine learning algorithms are extensively used to make increasingly more consequential decisions about people, so achieving optimal predictive performance can no longer be the only focus. A particularly important consideration is fairness…
Synthetic data has gained significant momentum thanks to sophisticated machine learning tools that enable the synthesis of high-dimensional datasets. However, many generation techniques do not give the data controller control over what…
The rise of deep learning (DL) has led to a surging demand for training data, which incentivizes the creators of DL models to trawl through the Internet for training materials. Meanwhile, users often have limited control over whether their…
Differential Privacy (DP) is often presented as a strong privacy-enhancing technology with broad applicability and advocated as a de-facto standard for releasing aggregate statistics on sensitive data. However, in many embodiments, DP…
An information theoretic privacy mechanism design problem for two scenarios is studied where the private data is either hidden or observable. In each scenario, privacy leakage constraints are considered using two different measures. In…
Fairness monitoring is critical for detecting algorithmic bias, as mandated by the EU AI Act. Since such monitoring requires sensitive user data (e.g., ethnicity), the AI Act permits its processing only with strict privacy measures, such as…
Data encryption limits the power and efficiency of queries. Direct processing of encrypted data should ideally be possible to avoid the need for data decryption, processing, and re-encryption. It is vital to keep the data searchable and…
The problem of publishing privacy-guaranteed data for hypothesis testing is studied using the maximal leakage (ML) as a metric for privacy and the type-II error exponent as the utility metric. The optimal mechanism (random mapping) that…
The most prevalent notions of fairness in machine learning are statistical definitions: they fix a small collection of pre-defined groups, and then ask for parity of some statistic of the classifier across these groups. Constraints of this…
Consider a source and multiple users who observe the independent and identically distributed (i.i.d.) copies of correlated Gaussian random variables. The source wishes to compress its observations and store the result in a public database…
To comply with emerging privacy laws and regulations, it has become common for applications like electronic health records systems (EHRs) to collect access logs, which record each time a user (e.g., a hospital employee) accesses a piece of…
The problem of optimal authorization of a user in a system with a role-based access control policy is considered. The main criterion is to minimize the risks of permission leakage. The choice of the role for authorization is based on the…
Auditors need robust methods to assess the compliance of web platforms with the law. However, since they hardly ever have access to the algorithm, implementation, or training data used by a platform, the problem is harder than a simple…
Responsible use of machine learning requires models to be audited for undesirable properties. While a body of work has proposed using explanations for auditing, how to do so and why has remained relatively ill-understood. This work…
Federated learning (FL) has attracted widespread attention because it supports the joint training of models by multiple participants without moving private dataset. However, there are still many security issues in FL that deserve…
It is well-known that neural networks can unintentionally memorize their training examples, causing privacy concerns. However, auditing memorization in large non-auto-regressive automatic speech recognition (ASR) models has been challenging…
\emph{Literate programming}, introduced by Knurth, interleaves code and prose so that a program can be read as both executable and explanatory text. We propose \emph{literate execution}, which inverts this relationship: rather than…