Related papers: McFIL: Model Counting Functionality-Inherent Leaka…
We consider a collaborative learning scenario in which multiple data-owners wish to jointly train a logistic regression model, while keeping their individual datasets private from the other parties. We propose COPML, a fully-decentralized…
As Large Language Models (LLMs) become integral to scientific workflows, concerns over the confidentiality and ethical handling of confidential data have emerged. This paper explores data exposure risks through LLM-powered scientific tools,…
Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that…
We introduce a tunable measure for information leakage called maximal alpha-leakage. This measure quantifies the maximal gain of an adversary in inferring any (potentially random) function of a dataset from a release of the data. The…
Quantitative theories of information flow give us an approach to relax the absolute confidentiality properties that are difficult to satisfy for many practical programs. The classical information-theoretic approaches for sequential…
The widespread adoption of smart meters provides access to detailed and localized load consumption data, suitable for training building-level load forecasting models. To mitigate privacy concerns stemming from model-induced data leakage,…
Cryptographic research takes software timing side channels seriously. Approaches to mitigate them include constant-time coding and techniques to enforce such practices. However, recent attacks like Meltdown [42], Spectre [37], and…
Cross-silo federated learning allows multiple organizations to collaboratively train machine learning models without sharing raw data, but client updates can still leak sensitive information through inference attacks. Secure aggregation…
Numerous studies have underscored the significant privacy risks associated with various leakage patterns in encrypted data stores. While many solutions have been proposed to mitigate these leakages, they either (1) incur substantial…
Physical implementations of cryptographic algorithms leak information, which makes them vulnerable to so-called side-channel attacks. The problem of secure computation in the presence of leakage is generally known as leakage resilience. In…
Cache timing attacks allow attackers to infer the properties of a secret execution by observing cache hits and misses. But how much information can actually leak through such attacks? For a given program, a cache model, and an input, our…
Privacy preservation in distributed computations is an important subject as digitization and new technologies enable collection and storage of vast amounts of data, including private data belonging to individuals. To this end, there is a…
With the increased attention and legislation for data-privacy, collaborative machine learning (ML) algorithms are being developed to ensure the protection of private data used for processing. Federated learning (FL) is the most popular of…
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…
Collaborative learning enables two or more participants, each with their own training dataset, to collaboratively learn a joint model. It is desirable that the collaboration should not cause the disclosure of either the raw datasets of each…
Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…
In this paper we describe a method for verifying secure information flow of programs, where apart from direct and indirect flows a secret information can be leaked through covert timing channels. That is, no two computations of a program…
We establish a simple connection between robust and differentially-private algorithms: private mechanisms which perform well with very high probability are automatically robust in the sense that they retain accuracy even if a constant…
Formal verification of power side-channel leakage and its countermeasures in cryptographic algorithms is challenging, as SAT-based methods fail to scale on XOR-heavy, time-unrolled cryptographic circuits with realistic leakage models. We…
Formal Concept Analysis (FCA) is extensively used in knowledge extraction, cognitive concept learning, and data mining. However, its computational demands on large-scale datasets often require outsourcing to external computing services,…