Related papers: PUTWorkbench: Analysing Privacy in AI-intensive Sy…
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…
Information density and its exponential form, known as lift, play a central role in information privacy leakage measures. $\alpha$-lift is the power-mean of lift, which is tunable between the worst-case measure max-lift ($\alpha=\infty$)…
The rapid integration of AI-powered coding assistants into developer workflows has raised significant privacy and trust concerns. As developers entrust proprietary code to services like OpenAI's GPT, Google's Gemini, and GitHub Copilot, the…
The proliferation of AI agents, with their complex and context-dependent actions, renders conventional privacy paradigms obsolete. This position paper argues that the current model of privacy management, rooted in a user's unilateral…
Privacy preserving machine learning deployments in sensitive deep learning applications; from medical imaging to autonomous systems; increasingly require combining multiple techniques. Yet, practitioners lack systematic guidance to assess…
Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\epsilon$, about how much information is leaked by a mechanism. However, implementations of privacy-preserving…
Romantic AI platforms invite intimate emotional disclosure, yet their data governance practices remain underexamined. This preliminary study analyses the Privacy Policies and Terms of Service of six Western and Chinese romantic AI…
Supporting users in protecting sensitive information when using conversational agents (CAs) is crucial, as users may undervalue privacy protection due to outdated, partial, or inaccurate knowledge about privacy in CAs. Although privacy…
This paper introduces AIJack, an open-source library designed to assess security and privacy risks associated with the training and deployment of machine learning models. Amid the growing interest in big data and AI, advancements in machine…
The design and development process for Internet of Things (IoT) applications is more complicated than for desktop, mobile, or web applications. IoT applications require both software and hardware to work together across multiple different…
Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator…
Differential privacy (DP) is a compelling privacy definition that explains the privacy-utility tradeoff via formal, provable guarantees. Inspired by recent progress toward general-purpose data release algorithms, we propose a private…
The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models…
The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the complex interplay between privacy, verifiability, and…
Artificial Intelligence (AI) tools such as GitHub Copilot and ChatGPT are increasingly used in software engineering (SE) for tasks such as code, test, and documentation generation. However, engineers often face uncertainty about when to…
A privacy mechanism design problem is studied through the lens of information theory. In this work, an agent observes useful data $Y=(Y_1,...,Y_N)$ that is correlated with private data $X=(X_1,...,X_N)$ which is assumed to be also…
LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what may and must not be shared, and the agent must robustly follow that intent even when…
The increasing integration of artificial intelligence (AI) in digital ecosystems has reshaped privacy dynamics, particularly for young digital citizens navigating data-driven environments. This study explores evolving privacy concerns…
Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance. However, it requires sending data to annotators for labeling. This presents a possible privacy leak when the…
The design of a statistical signal processing privacy problem is studied where the private data is assumed to be observable. In this work, an agent observes useful data $Y$, which is correlated with private data $X$, and wants to disclose…