Related papers: Comment on "An Efficient Privacy-Preserving Ranked…
Retrieval-Augmented Generation (RAG) has become a foundational component of modern AI systems, yet it introduces significant privacy risks by exposing user queries to service providers. To address this, we introduce PIR-RAG, a practical…
Classification of personal text messages has many useful applications in surveillance, e-commerce, and mental health care, to name a few. Giving applications access to personal texts can easily lead to (un)intentional privacy violations. We…
Daily, massive volume of data are produced due to the internet of things' rapid development, which has now permeated the healthcare industry. Recent advances in data mining have spawned a new field of a study dubbed privacy-preserving data…
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…
Proper privacy protection in RFID systems is important. However, many of the schemes known are impractical, either because they use hash functions instead of the more hardware efficient symmetric encryption schemes as a efficient…
Privacy concerns in outsourced cloud databases have become more and more important recently and many efficient and scalable query processing methods over encrypted data have been proposed. However, there is very limited work on how to…
In this paper, we address the problem of secure distributed computation in scenarios where user data is not uniformly distributed, extending existing frameworks that assume uniformity, an assumption that is challenging to enforce in data…
Existing work on privacy-preserving machine learning with Secure Multiparty Computation (MPC) is almost exclusively focused on model training and on inference with trained models, thereby overlooking the important data pre-processing stage.…
With the increasing popularity of the cloud, clients oursource their data to clouds in order to take advantage of unlimited virtualized storage space and the low management cost. Such trend prompts the privately oursourcing computation,…
Distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis. However, such frameworks are vulnerable to privacy leakage attacks from shared…
Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. Whereas extensive research has demonstrated the privacy risks of large…
Users worldwide access massive amounts of curated data in the form of rankings on a daily basis. The societal impact of this ease of access has been studied and work has been done to propose and enforce various notions of fairness in…
The fast development of large language models (LLMs) and popularization of cloud computing have led to increasing concerns on privacy safeguarding and data security of cross-cloud model deployment and training as the key challenges. We…
Prompt injection attacks are an emerging threat to large language models (LLMs), enabling malicious users to manipulate outputs through carefully designed inputs. Existing detection approaches often require centralizing prompt data,…
In this paper, we design the multi-class privacy$\text{-}$preserving cloud computing scheme (MPCC) leveraging compressive sensing for compact sensor data representation and secrecy for data encryption. The proposed scheme achieves two-class…
Privacy-preserving machine learning (PPML) is critical to ensure data privacy in AI. Over the past few years, the community has proposed a wide range of provably secure PPML schemes that rely on various cryptography primitives. However,…
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…
We propose a method to protect the privacy of search engine users by decomposing the queries using semantically \emph{related} and unrelated \emph{distractor} terms. Instead of a single query, the search engine receives multiple decomposed…
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…
Consumers frequently interact with reputation systems to rate products, services, and deliveries. While past research extensively studied different conceptual approaches to realize such systems securely and privacy-preservingly, these…