Related papers: Prochlo: Strong Privacy for Analytics in the Crowd
How are AI assistants being used in the real world? While model providers in theory have a window into this impact via their users' data, both privacy concerns and practical challenges have made analyzing this data difficult. To address…
Audio signals can reveal intimate details about a person's life, including their conversations, health status, emotions, location, and personal preferences. Unauthorized access or misuse of this information can have profound personal and…
Crowd scene analysis receives growing attention due to its wide applications. Grasping the accurate crowd location (rather than merely crowd count) is important for spatially identifying high-risk regions in congested scenes. In this paper,…
Smart devices with built-in sensors, computational capabilities, and network connectivity have become increasingly pervasive. The crowds of smart devices offer opportunities to collectively sense and perform computing tasks in an…
Much of machine learning relies on the use of large amounts of data to train models to make predictions. When this data comes from multiple sources, for example when evaluation of data against a machine learning model is offered as a…
Profiling techniques are used extensively at different parts of the computing stack to achieve many goals. One major goal is to make a piece of software execute more efficiently on a specific hardware platform, where efficiency spans…
Side Channel Analysis (SCA) relaxes the black-box assumption of conventional cryptanalysis by incorporating physical measurements acquired during cryptographic operations. Electro-magnetic (EM) emissions of a chip during computations often…
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…
In the current paradigm of digital personalized services, the centralized management of personal data raises significant privacy concerns, security vulnerabilities, and diminished individual autonomy over sensitive information. Despite…
Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML's pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential…
Malicious encryption techniques continue to evolve, bypassing conventional detection mechanisms that rely on static signatures or predefined behavioral rules. Spectral analysis presents an alternative approach that transforms system…
Machine Learning (ML) techniques have begun to dominate data analytics applications and services. Recommendation systems are a key component of online service providers. The financial industry has adopted ML to harness large volumes of data…
An increasing amount of sensitive information today is stored electronically and a substantial part of this information (e.g., health records, tax data, legal documents) must be retained over long time periods (e.g., several decades or even…
Microcontroller-based embedded systems are vital in daily life, but are especially vulnerable to control-flow hijacking attacks due to hardware and software constraints. Control-Flow Attestation (CFA) aims to precisely attest the execution…
We present a practical framework to deploy privacy-preserving machine learning (PPML) applications in untrusted clouds based on a trusted execution environment (TEE). Specifically, we shield unmodified PyTorch ML applications by running…
An important aspect of crowd monitoring is knowing how many people we are dealing with. Sometimes, knowing the size of a crowd in a single location and at a specific moment is enough. Matters become problematic when counting the same people…
In this paper, we consider the privacy preservation problem in both discrete- and continuous-time average consensus algorithms with strongly connected and balanced graphs, against either internal honest-but-curious agents or external…
Federated Learning, as a popular paradigm for collaborative training, is vulnerable against privacy attacks. Different privacy levels regarding users' attitudes need to be satisfied locally, while a strict privacy guarantee for the global…
Federated analytics (FA) is a privacy-preserving framework for computing data analytics over multiple remote parties (e.g., mobile devices) or silo-ed institutional entities (e.g., hospitals, banks) without sharing the data among parties.…
Distributed communities of researchers rely increasingly on valuable, proprietary, or sensitive datasets. Given the growth of such data, especially in fields new to data-driven, computationally intensive research like the social sciences…