Search Results for author: Giulia Fanti

Found 18 papers, 14 papers with code

On the Privacy Properties of GAN-generated Samples

no code implementations3 Jun 2022 Zinan Lin, Vyas Sekar, Giulia Fanti

By drawing connections to the generalization properties of GANs, we prove that under some assumptions, GAN-generated samples inherently satisfy some (weak) privacy guarantees.

Towards a Defense against Backdoor Attacks in Continual Federated Learning

1 code implementation24 May 2022 Shuaiqi Wang, Jonathan Hayase, Giulia Fanti, Sewoong Oh

Backdoor attacks are a major concern in federated learning (FL) pipelines where training data is sourced from untrusted clients over long periods of time (i. e., continual learning).

Continual Learning Federated Learning

RareGAN: Generating Samples for Rare Classes

1 code implementation20 Mar 2022 Zinan Lin, Hao Liang, Giulia Fanti, Vyas Sekar

We study the problem of learning generative adversarial networks (GANs) for a rare class of an unlabeled dataset subject to a labeling budget.

Active Learning

FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning

no code implementations ICLR 2022 Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh

We propose FedChain, an algorithmic framework that combines the strengths of local methods and global methods to achieve fast convergence in terms of R while leveraging the similarity between clients.

Federated Learning Image Classification

Self-Supervised Euphemism Detection and Identification for Content Moderation

1 code implementation31 Mar 2021 Wanzheng Zhu, Hongyu Gong, Rohan Bansal, Zachary Weinberg, Nicolas Christin, Giulia Fanti, Suma Bhat

It is usually apparent to a human moderator that a word is being used euphemistically, but they may not know what the secret meaning is, and therefore whether the message violates policy.

Word Embeddings

Efficient Algorithms for Federated Saddle Point Optimization

no code implementations12 Feb 2021 Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh

Our goal is to design an algorithm that can harness the benefit of similarity in the clients while recovering the Minibatch Mirror-prox performance under arbitrary heterogeneity (up to log factors).

Why Spectral Normalization Stabilizes GANs: Analysis and Improvements

1 code implementation NeurIPS 2021 Zinan Lin, Vyas Sekar, Giulia Fanti

Spectral normalization (SN) is a widely-used technique for improving the stability and sample quality of Generative Adversarial Networks (GANs).

SquirRL: Automating Attack Discovery on Blockchain Incentive Mechanisms with Deep Reinforcement Learning

1 code implementation4 Dec 2019 Charlie Hou, Mingxun Zhou, Yan Ji, Phil Daian, Florian Tramer, Giulia Fanti, Ari Juels

Incentive mechanisms are central to the functionality of permissionless blockchains: they incentivize participants to run and secure the underlying consensus protocol.

Cryptography and Security

Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions

3 code implementations30 Sep 2019 Zinan Lin, Alankar Jain, Chen Wang, Giulia Fanti, Vyas Sekar

By shedding light on the promise and challenges, we hope our work can rekindle the conversation on workflows for data sharing.

Synthetic Data Generation Time Series

Prism: Scaling Bitcoin by 10,000x

2 code implementations25 Sep 2019 Lei Yang, Vivek Bagaria, Gerui Wang, Mohammad Alizadeh, David Tse, Giulia Fanti, Pramod Viswanath

Bitcoin is the first fully decentralized permissionless blockchain protocol and achieves a high level of security: the ledger it maintains has guaranteed liveness and consistency properties as long as the adversary has less compute power than the honest nodes.

Distributed, Parallel, and Cluster Computing Cryptography and Security Networking and Internet Architecture

InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs

1 code implementation14 Jun 2019 Zinan Lin, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh

Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution.

Disentanglement Model Selection

PacGAN: The power of two samples in generative adversarial networks

7 code implementations NeurIPS 2018 Zinan Lin, Ashish Khetan, Giulia Fanti, Sewoong Oh

Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples.

Two-sample testing

Deanonymization in the Bitcoin P2P Network

1 code implementation NeurIPS 2017 Giulia Fanti, Pramod Viswanath

Recent attacks on Bitcoin's peer-to-peer (P2P) network demonstrated that its transaction-flooding protocols, which are used to ensure network consistency, may enable user deanonymization---the linkage of a user's IP address with her pseudonym in the Bitcoin network.

Dandelion: Redesigning the Bitcoin Network for Anonymity

2 code implementations16 Jan 2017 Shaileshh Bojja Venkatakrishnan, Giulia Fanti, Pramod Viswanath

We propose a simple networking policy called Dandelion, which achieves nearly-optimal anonymity guarantees at minimal cost to the network's utility.

Cryptography and Security Information Theory Information Theory

Building a RAPPOR with the Unknown: Privacy-Preserving Learning of Associations and Data Dictionaries

1 code implementation4 Mar 2015 Giulia Fanti, Vasyl Pihur, Úlfar Erlingsson

Techniques based on randomized response enable the collection of potentially sensitive data from clients in a privacy-preserving manner with strong local differential privacy guarantees.

Cryptography and Security

Spy vs. Spy: Rumor Source Obfuscation

no code implementations29 Dec 2014 Giulia Fanti, Peter Kairouz, Sewoong Oh, Pramod Viswanath

Whether for fear of judgment or personal endangerment, it is crucial to keep anonymous the identity of the user who initially posted a sensitive message.

Cannot find the paper you are looking for? You can Submit a new open access paper.