Related papers: Curator Attack: When Blackbox Differential Privacy…
Local differential privacy (LDP) offers rigorous, quantifiable privacy guarantees for personal data by introducing perturbations at the data source. Understanding how these perturbations affect classifier utility is crucial for both…
Audits are critical mechanisms for identifying the risks and limitations of deployed artificial intelligence (AI) systems. However, the effective execution of AI audits remains incredibly difficult, and practitioners often need to make use…
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 voluntary donation of private health information for altruistic purposes, such as supporting research advancements, is a common practice. However, concerns about data misuse and leakage may deter people from donating their information.…
Although essential to revealing biased performance, well intentioned attempts at algorithmic auditing can have effects that may harm the very populations these measures are meant to protect. This concern is even more salient while auditing…
Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…
Introduction: The use of chatbots is becoming increasingly important across various aspects of daily life. However, the privacy concerns associated with these communications have not yet been thoroughly addressed. The aim of this study was…
Data privacy is critical in instilling trust and empowering the societal pacts of modern technology-driven democracies. Unfortunately, it is under continuous attack by overreaching or outright oppressive governments, including some of the…
In a technical treatment, this article establishes the necessity of transparent privacy for drawing unbiased statistical inference for a wide range of scientific questions. Transparency is a distinct feature enjoyed by differential privacy:…
GitHub provides developers with a practical way to distribute source code and collaboratively work on common projects. To enhance account security and privacy, GitHub allows its users to manage access permissions, review audit logs, and…
The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for reliable compliance auditing. For binary classifiers,…
A fundamental problem in differential privacy is to release a privatized data structure over a dataset that can be used to answer a class of linear queries with small errors. This problem has been well studied in the static case. In this…
Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…
Differential privacy is a rigorous mathematical framework for evaluating and protecting data privacy. In most existing studies, there is a vulnerable assumption that records in a dataset are independent when differential privacy is applied.…
Current consumer-protection debates focus on the powerful new data-analysis techniques that have disrupted the balance of power between companies and their customers. Online tracking enables sellers to amass troves of historical data, apply…
An increasing number of open-source libraries promise to bring differential privacy to practice, even for non-experts. This paper studies five libraries that offer differentially private analytics: Google DP, SmartNoise, diffprivlib,…
A commonly used method to protect user privacy in data collection is to perform randomized perturbation on user's real data before collection so that aggregated statistics can still be inferred without endangering secrets held by…
Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the…
A growing body of literature has proposed formal approaches to audit algorithmic systems for biased and harmful behaviors. While formal auditing approaches have been greatly impactful, they often suffer major blindspots, with critical…
Over the last decade there have been great strides made in developing techniques to compute functions privately. In particular, Differential Privacy gives strong promises about conclusions that can be drawn about an individual. In contrast,…