Sciweavers

8381 search results - page 177 / 1677
» The security of machine learning
Sort
View
CCS
2009
ACM
16 years 5 months ago
Automatic discovery of botnet communities on large-scale communication networks
Botnets are networks of compromised computers infected with malicious code that can be controlled remotely under a common command and control (C&C) channel. Recognized as one ...
Wei Lu, Mahbod Tavallaee, Ali A. Ghorbani
ICML
2007
IEEE
16 years 5 months ago
An empirical evaluation of deep architectures on problems with many factors of variation
Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only b...
Hugo Larochelle, Dumitru Erhan, Aaron C. Courville...
127
Voted
ECML
2003
Springer
15 years 10 months ago
A New Way to Introduce Knowledge into Reinforcement Learning
We present in this paper a method to introduce a priori knowledge into reinforcement learning using temporally extended actions. The aim of our work is to reduce the learning time ...
Pascal Garcia
OOPSLA
2001
Springer
15 years 9 months ago
Multitasking without Compromise: A Virtual Machine Evolution
The Multitasking Virtual Machine (called from now on simply MVM) is a modification of the Java™ virtual machine. It enables safe, secure, and scalable multitasking. Safety is ac...
Grzegorz Czajkowski, Laurent Daynès
140
Voted
SP
2003
IEEE
15 years 10 months ago
Using Memory Errors to Attack a Virtual Machine
We present an experimental study showing that soft memory errors can lead to serious security vulnerabilities in Java and .NET virtual machines, or in any system that relies on ty...
Sudhakar Govindavajhala, Andrew W. Appel