Sciweavers

658 search results - page 52 / 132
» Open problems in the security of learning
Sort
View
DMKD
2003
ACM
151views Data Mining» more  DMKD 2003»
14 years 3 months ago
Assuring privacy when big brother is watching
Homeland security measures are increasing the amount of data collected, processed and mined. At the same time, owners of the data raised legitimate concern about their privacy and...
Murat Kantarcioglu, Chris Clifton
JMLR
2010
148views more  JMLR 2010»
13 years 4 months ago
A Generalized Path Integral Control Approach to Reinforcement Learning
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Evangelos Theodorou, Jonas Buchli, Stefan Schaal
STOC
2006
ACM
170views Algorithms» more  STOC 2006»
14 years 10 months ago
Hardness of approximate two-level logic minimization and PAC learning with membership queries
Producing a small DNF expression consistent with given data is a classical problem in computer science that occurs in a number of forms and has numerous applications. We consider ...
Vitaly Feldman
ISF
2008
114views more  ISF 2008»
13 years 10 months ago
An OVAL-based active vulnerability assessment system for enterprise computer networks
Abstract Many security problems are caused by vulnerabilities hidden in enterprise computer networks. It is very important for system administrators to have knowledge about the sec...
Xiuzhen Chen, Qinghua Zheng, Xiaohong Guan
EUROCRYPT
2000
Springer
14 years 1 months ago
Exposure-Resilient Functions and All-or-Nothing Transforms
Abstract. We study the problem of partial key exposure. Standard cryptographic definitions and constructions do not guarantee any security even if a tiny fraction of the secret key...
Ran Canetti, Yevgeniy Dodis, Shai Halevi, Eyal Kus...