Sciweavers

3556 search results - page 104 / 712
» Can machine learning be secure
Sort
View
CCS
2009
ACM
14 years 11 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
ACSAC
2007
IEEE
14 years 4 months ago
Retrofitting the IBM POWER Hypervisor to Support Mandatory Access Control
Server virtualization more readily enables the collocation of disparate workloads on a shared physical platform. When employed on systems across a data center, the result can be a...
Enriquillo Valdez, Reiner Sailer, Ronald Perez
WETICE
2000
IEEE
14 years 2 months ago
Towards Secure e-Services
This poster paper presents a work in progress in the new emerging area of electronic services (e-services). The networked home with refrigerators and washing machines connected to...
Claudiu Duma, Almut Herzog, Nahid Shahmehri
NSDI
2008
14 years 19 days ago
Securing Distributed Systems with Information Flow Control
Recent operating systems [12, 21, 26] have shown that decentralized information flow control (DIFC) can secure applications built from mostly untrusted code. This paper extends DI...
Nickolai Zeldovich, Silas Boyd-Wickizer, David Maz...
ICML
1998
IEEE
14 years 11 months ago
The Case against Accuracy Estimation for Comparing Induction Algorithms
We analyze critically the use of classi cation accuracy to compare classi ers on natural data sets, providing a thorough investigation using ROC analysis, standard machine learnin...
Foster J. Provost, Tom Fawcett, Ron Kohavi