Security Evaluation of Pattern Classifiers in Adversarial Environments

Download Now
Provided by: International Journal of Computer Science and Mobile Computing (IJCSMC)
Topic: Security
Format: PDF
Pattern classification systems are commonly used in adversarial applications, like biometric authentication, network intrusion detection and spam filtering, in which data can be purposely manipulated by humans to undermine their operation. As this adversarial scenario is not taken into account by classical design methods, pattern classification systems may exhibit vulnerabilities, whose exploitation may severely affect their performance, and consequently limit their practical utility. Several works have addressed the problem of designing robust classifiers against these threats, although mainly focusing on specific applications and kinds of attacks.
Download Now

Find By Topic