Sciweavers

3556 search results - page 227 / 712
» Can machine learning be secure
Sort
View
CRYPTO
2012
Springer
217views Cryptology» more  CRYPTO 2012»
13 years 7 months ago
Securing Circuits against Constant-Rate Tampering
We present a compiler that converts any circuit into one that remains secure even if a constant fraction of its wires are tampered with. Following the seminal work of Ishai et al. ...
Dana Dachman-Soled, Yael Tauman Kalai
148
Voted
NDSS
2003
IEEE
15 years 10 months ago
Traps and Pitfalls: Practical Problems in System Call Interposition Based Security Tools
System call interposition is a powerful method for regulating and monitoring application behavior. In recent years, a wide variety of security tools have been developed that use t...
Tal Garfinkel
STOC
2005
ACM
198views Algorithms» more  STOC 2005»
16 years 5 months ago
On lattices, learning with errors, random linear codes, and cryptography
Our main result is a reduction from worst-case lattice problems such as GAPSVP and SIVP to a certain learning problem. This learning problem is a natural extension of the `learnin...
Oded Regev
INCDM
2010
Springer
138views Data Mining» more  INCDM 2010»
15 years 3 months ago
Learning Discriminative Distance Functions for Case Retrieval and Decision Support
The importance of learning distance functions is gradually being acknowledged by the machine learning community, and different techniques are suggested that can successfully learn ...
Alexey Tsymbal, Martin Huber, Shaohua Kevin Zhou
PADS
2009
ACM
15 years 11 months ago
Real-Time Security Exercises on a Realistic Interdomain Routing Experiment Platform
We use a realistic interdomain routing experiment platform to conduct real-time attack and defense exercises for training purposes. Our interdomain routing experiment platform int...
Yue Li, Michael Liljenstam, Jason Liu