• Publications
  • Influence
Deep Learning with Differential Privacy
TLDR
We combine state-of-the-art machine learning methods with advanced privacy-preserving mechanisms, training neural networks within a modest (“single-digit”) privacy budget. Expand
  • 1,541
  • 353
  • PDF
Our Data, Ourselves: Privacy Via Distributed Noise Generation
TLDR
In this work we provide efficient distributed protocols for generating shares of random noise, secure against malicious participants. Expand
  • 1,159
  • 134
  • PDF
Rényi Differential Privacy
  • Ilya Mironov
  • Computer Science
  • IEEE 30th Computer Security Foundations Symposium…
  • 24 February 2017
TLDR
We propose a natural relaxation of differential privacy based on the Rényi divergence. Expand
  • 326
  • 83
  • PDF
Differentially private recommender systems: building privacy into the net
TLDR
We consider the problem of producing recommendations from collective user behavior while simultaneously providing guarantees of privacy for these users. Expand
  • 612
  • 53
  • PDF
Frodo: Take off the Ring! Practical, Quantum-Secure Key Exchange from LWE
TLDR
We demonstrate that LWE-based key exchange is quite practical: our constant time implementation requires around 1.3ms computation time for each party; compared to the recent NewHope R-LWE scheme, communication sizes increase by a factor of 4.7x, but remain under 12 KiB. Expand
  • 238
  • 44
  • PDF
Cache-Collision Timing Attacks Against AES
TLDR
This paper describes a general attack strategy using a simplified model of the cache to predict timing variation due to cache-collisions in the sequence of lookups performed by the encryption. Expand
  • 336
  • 28
  • PDF
Scalable Private Learning with PATE
TLDR
We introduce new noisy aggregation mechanisms for teacher ensembles that are more selective and add less noise, and prove their tighter differential-privacy guarantees. Expand
  • 204
  • 28
  • PDF
Uncheatable Distributed Computations
TLDR
We propose security schemes that defend against cheating by untrusted participants in distributed computations with very little overhead. Expand
  • 258
  • 21
  • PDF
Incentives for sharing in peer-to-peer networks
TLDR
We consider the free-rider problem that arises in peer-to-peer file sharing networks such as Napster, by constructing a formal game theoretic model of the system and analyzing equilibria of user strategies under several novel payment mechanisms. Expand
  • 583
  • 19
  • PDF
Prochlo: Strong Privacy for Analytics in the Crowd
TLDR
The large-scale monitoring of computer users' software activities has become commonplace, e.g., for application telemetry, error reporting, or demographic profiling. Expand
  • 141
  • 18
  • PDF
...
1
2
3
4
5
...