The Curious Case of the PDF Converter that Likes Mozart: Dissecting and Mitigating the Privacy Risk of Personal Cloud Apps

Related publications (30)

About
Privacy
Disclaimer

Graph Chatbot

Arbitrary Decisions are a Hidden Cost of Differentially Private Training

Carmela González Troncoso, Bogdan Kulynych

Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data (e.g., adding Ga ...

Assoc Computing Machinery2023

Sustainability and Ethicality are Peripheral to Students’ Software Design

Bryan Alexander Ford, Siara Ruth Isaac, Pierluca Borsò, Aditi Kothiyal

The conceptual design phase is a fascinating moment to observe how a design task is interpreted, as the (often implicit) relative importance students accord to the various requirements and constraints offers a window into the thinking underpinning their de ...

Tempus Publications2023

A Practical Influence Approximation for Privacy-Preserving Data Filtering in Federated Learning

Boi Faltings, Ljubomir Rokvic, Panayiotis Danassis

Federated Learning by nature is susceptible to low-quality, corrupted, or even malicious data that can severely degrade the quality of the learned model. Traditional techniques for data valuation cannot be applied as the data is never revealed. We present ...

2023

Privacy-preserving federated neural network training and inference

Sinem Sav

Training accurate and robust machine learning models requires a large amount of data that is usually scattered across data silos. Sharing, transferring, and centralizing the data from silos, however, is difficult due to current privacy regulations (e.g., H ...

EPFL2023

Enforcing Privacy in Distributed Learning With Performance Guarantees

Ali H. Sayed, Stefan Vlaski, Elsa Rizk

We study the privatization of distributed learning and optimization strategies. We focus on differential privacy schemes and study their effect on performance. We show that the popular additive random perturbation scheme degrades performance because it is ...

Ieee-Inst Electrical Electronics Engineers Inc2023

On the (In)security of Peer-to-Peer Decentralized Machine Learning

Carmela González Troncoso, Mathilde Aliénor Raynal, Dario Pasquini

In this work, we carry out the first, in-depth, privacy analysis of Decentralized Learning-a collaborative machine learning framework aimed at addressing the main limitations of federated learning. We introduce a suite of novel attacks for both passive and ...

IEEE COMPUTER SOC2023

Anonymous Tokens with Stronger Metadata Bit Hiding from Algebraic MACs

Serge Vaudenay, Fatma Betül Durak

On the one hand, the web needs to be secured from malicious activities such as bots or DoS attacks; on the other hand, such needs ideally should not justify services tracking people's activities on the web. Anonymous tokens provide a nice tradeoff between ...

2023

Not Yet Another Digital ID: Privacy-Preserving Humanitarian Aid Distribution

Carmela González Troncoso, Boya Wang, Wouter Lueks, Justinas Sukaitis

Humanitarian aid-distribution programs help bring physical goods to people in need. Traditional paper-based solutions to support aid distribution do not scale to large populations and are hard to secure. Existing digital solutions solve these issues, at th ...

IEEE COMPUTER SOC2023

Efficient and Accurate Peer-to-Peer Training of Machine Learning Based Home Thermal Models

Rachid Guerraoui, Alexandre David Olivier Maurer, Omid Ardakanian

The integration of smart thermostats in home automation systems has created an opportunity to optimize space heating and cooling through the use of machine learning, for example for thermal model identification. Nonetheless, its full potential remains unta ...

Assoc Computing Machinery2023

On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Rachid Guerraoui, John Stephan, Youssef Allouah, Nirupam Gupta, Rafaël Benjamin Pinot

The ubiquity of distributed machine learning (ML) in sensitive public domain applications calls for algorithms that protect data privacy, while being robust to faults and adversarial behaviors. Although privacy and robustness have been extensively studied ...

2023

Page 2 of 3