This contrastive regularizer is inspired by a natural notion of disentanglement: latent traversal.
By drawing connections to the generalization properties of GANs, we prove that under some assumptions, GAN-generated samples inherently satisfy some (weak) privacy guarantees.
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).
We study the problem of learning generative adversarial networks (GANs) for a rare class of an unlabeled dataset subject to a labeling budget.
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.
Abusive language is a massive problem in online social platforms.
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.
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).
Incentive mechanisms are central to the functionality of permissionless blockchains: they incentivize participants to run and secure the underlying consensus protocol.
Cryptography and Security
By shedding light on the promise and challenges, we hope our work can rekindle the conversation on workflows for data sharing.
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
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.
Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples.
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.
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
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
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.