Related papers: PrivacyBench: A Conversational Benchmark for Evalu…
The development of privacy-enhancing technologies has made immense progress in reducing trade-offs between privacy and performance in data exchange and analysis. Similar tools for structured transparency could be useful for AI governance by…
Recent advancements in generative AI have made it possible to create synthetic datasets that can be as accurate as real-world data for training AI models, powering statistical insights, and fostering collaboration with sensitive datasets…
Despite the remarkable advances of Large Language Models (LLMs) across diverse cognitive tasks, the rapid enhancement of these capabilities also introduces emergent deceptive behaviors that may induce severe risks in high-stakes…
Generative models are increasingly used to produce privacy-preserving synthetic data as a safe alternative to sharing sensitive training datasets. However, we demonstrate that such synthetic releases can still leak information about the…
Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and…
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…
To enable personalized and context-aware interactions, conversational AI systems have introduced a new mechanism: Memory. Memory creates what we refer to as the Algorithmic Self-portrait - a new form of personalization derived from users'…
Membership Inference Attacks have emerged as a dominant method for empirically measuring privacy leakage from machine learning models. Here, privacy is measured by the {\em{advantage}} or gap between a score or a function computed on the…
Privacy is a human right. It ensures that individuals are free to engage in discussions, participate in groups, and form relationships online or offline without fear of their data being inappropriately harvested, analyzed, or otherwise used…
According to GitGuardian's monitoring of public GitHub repositories, the exposure of secrets (API keys and other credentials) increased two-fold in 2021 compared to 2020, totaling more than six million secrets. However, no benchmark dataset…
Training data privacy has been a top concern in AI modeling. While methods like differentiated private learning allow data contributors to quantify acceptable privacy loss, model utility is often significantly damaged. In practice,…
Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge bases, but this advancement introduces significant privacy risks. Existing privacy attacks on RAG systems can trigger data…
The current "notice and consent" paradigm is broken: consent dialogues are often manipulative, and users cannot realistically read or understand every privacy policy. While recent LLM-based tools empower users seeking active control, many…
Artificial Intelligence (AI) systems are frequently employed in online services to provide personalized experiences to users based on large collections of data. However, AI systems can be designed in different ways, with black-box AI…
Transfer learning through the use of pre-trained models has become a growing trend for the machine learning community. Consequently, numerous pre-trained models are released online to facilitate further research. However, it raises…
Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These applications are trained on datasets from many FL…
Existing research on privacy-preserving Human Activity Recognition (HAR) typically evaluates methods against a binary paradigm: clear video versus a single privacy transformation. This limits cross-method comparability and obscures the…
This paper investigates the impacts of the rapidly evolving landscape of generative Artificial Intelligence (AI) development. Emphasis is given to how organizations grapple with a critical imperative: reevaluating their policies regarding…
Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and…
This paper presents a systematic evaluation of the privacy behaviors and attributes of eight recent, popular browser agents. Browser agents are software that automate Web browsing using large language models and ancillary tooling. However,…