Related papers: Opal: Private Memory for Personal AI
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…
Motivated by privacy preservation for outsourced data, data-oblivious external memory is a computational framework where a client performs computations on data stored at a semi-trusted server in a way that does not reveal her data to the…
We present a new oblivious RAM that supports variable-sized storage blocks (vORAM), which is the first ORAM to allow varying block sizes without trivial padding. We also present a new history-independent data structure (a HIRB tree) that…
Differential privacy has emerged as the main definition for private data analysis and machine learning. The {\em global} model of differential privacy, which assumes that users trust the data collector, provides strong privacy guarantees…
A vast amount of valuable data is produced and is becoming available for analysis as a result of advancements in smart cyber-physical systems. The data comes from various sources, such as healthcare, smart homes, smart vehicles, and often…
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'…
Oblivious RAM protocols (ORAMs) allow a client to access data from an untrusted storage device without revealing the access patterns. Typically, the ORAM adversary can observe both read and write accesses. Write-only ORAMs target a more…
Advancements in machine learning have fuelled the popularity of using AI decision algorithms in procedures such as bail hearings (Feller et al. 2016), medical diagnoses (Rajkomar et al. 2018; Esteva et al. 2019) and recruitment (Heilweil…
Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…
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…
The identity problem today is a data-sharing problem. Today the fixed attributes approach adopted by the consumer identity management industry provides only limited information about an individual, and therefore is of limited value to the…
This work presents Origami, which provides privacy-preserving inference for large deep neural network (DNN) models through a combination of enclave execution, cryptographic blinding, interspersed with accelerator-based computation. Origami…
The ability of machines to comprehend and produce language that is similar to that of humans has revolutionized sectors like customer service, healthcare, and finance thanks to the quick advances in Natural Language Processing (NLP), which…
Access patterns to data stored remotely create a side channel that is known to leak information even if the content of the data is encrypted. To protect against access pattern leakage, Oblivious RAM is a cryptographic primitive that…
We live in a world where our personal data are both valuable and vulnerable to misappropriation through exploitation of security vulnerabilities in online services. For instance, Dropbox, a popular cloud storage tool, has certain security…
Human interaction with the external world fundamentally involves the exchange of personal memory, whether with other individuals, websites, applications, or, in the future, AI agents. A significant portion of this interaction is redundant,…
The widespread adoption of Retrieval-Augmented Generation (RAG) systems in real-world applications has heightened concerns about the confidentiality and integrity of their proprietary knowledge bases. These knowledge bases, which play a…
Hardware enclaves such as Intel SGX are a promising technology for improving the security of databases outsourced to the cloud. These enclaves provide an execution environment isolated from the hypervisor/OS, and encrypt data in RAM.…
Ciphertexts of an order-preserving encryption (OPE) scheme preserve the order of their corresponding plaintexts. However, OPEs are vulnerable to inference attacks that exploit this preserved order. At another end, differential privacy has…
With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing…