Share This Author
RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
This paper describes and motivates RAPPOR, details its differential-privacy and utility guarantees, discusses its practical deployment and properties in the face of different attack models, and gives results of its application to both synthetic and real-world data.
Control-Flow Integrity provides a useful foundation for enforcing further security policies, as it is demonstrated with efficient software implementations of a protected shadow call stack and of access control for memory regions.
Control-flow integrity principles, implementations, and applications
Control-flow integrity provides a useful foundation for enforcing further security policies, as it is demonstrated with efficient software implementations of a protected shadow call stack and of access control for memory regions.
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
- Nicolas Papernot, Martín Abadi, Ú. Erlingsson, Ian J. Goodfellow, Kunal Talwar
- Computer ScienceICLR
- 18 October 2016
Private Aggregation of Teacher Ensembles (PATE) is demonstrated, in a black-box fashion, multiple models trained with disjoint datasets, such as records from different subsets of users, which achieves state-of-the-art privacy/utility trade-offs on MNIST and SVHN.
DryadLINQ: A System for General-Purpose Distributed Data-Parallel Computing Using a High-Level Language
It is shown that excellent absolute performance can be attained--a general-purpose sort of 1012 Bytes of data executes in 319 seconds on a 240-computer, 960- disk cluster--as well as demonstrating near-linear scaling of execution time on representative applications as the authors vary the number of computers used for a job.
Enforcing Forward-Edge Control-Flow Integrity in GCC & LLVM
Constraining dynamic control transfers is a common technique for mitigating software vulnerabilities. This defense has been widely and successfully used to protect return addresses and stack data;…
Scalable Private Learning with PATE
- Nicolas Papernot, Shuang Song, Ilya Mironov, A. Raghunathan, Kunal Talwar, Ú. Erlingsson
- Computer ScienceICLR
- 15 February 2018
This work shows how PATE can scale to learning tasks with large numbers of output classes and uncurated, imbalanced training data with errors, and introduces new noisy aggregation mechanisms for teacher ensembles that are more selective and add less noise, and prove their tighter differential-privacy guarantees.
XFI: software guards for system address spaces
This work has implemented XFI for Windows on the x86 architecture using binary rewriting and a simple, stand-alone verifier; the implementation's correctness depends on the verifier, but not on the rewriter.
IRM enforcement of Java stack inspection
- Ú. Erlingsson, F. Schneider
- Computer ScienceProceeding IEEE Symposium on Security and…
- 19 February 2000
Two implementations are given for Java's stack inspection access-control policy by generating an inlined reference monitor for a different formulation of the policy, demonstrating the power of the IRM approach for enforcing security policies.
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
- Nicholas Carlini, Chang Liu, Ú. Erlingsson, Jernej Kos, D. Song
- Computer ScienceUSENIX Security Symposium
- 22 February 2018
This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequence models---a common type of machine-learning model, and describes new, efficient procedures that can extract unique, secret sequences, such as credit card numbers.