Blaine Nelson

Learn More
Machine learning systems offer unparalled flexibility in dealing with evolving input in a variety of applications, such as intrusion detection systems and spam e-mail filtering. However, machine learning algorithms themselves can be a target of attack by a malicious adversary. This paper provides a framework for answering the question, "Can machine learning(More)
In this paper (expanded from an invited talk at AISEC 2010), we discuss an emerging field of study: adversarial machine learning---the study of effective machine learning techniques against an adversarial opponent. In this paper, we: give a taxonomy for classifying attacks against online machine learning algorithms; discuss application-specific factors that(More)
Machine learning’s ability to rapidly evolve to changing and complex situations has helped it become a fundamental tool for computer security. That adaptability is also a vulnerability: attackers can exploit machine learning systems. We present a taxonomy identifying and analyzing attacks against machine learning systems. We show how these classes influence(More)
In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system at test time by carefully manipulating attack samples. In this work, we present a simple but effective gradientbased(More)
Statistical machine learning techniques have recently garnered increased popularity as a means to improve network design and security. For intrusion detection, such methods build a model for normal behavior from training data and detect attacks as deviations from that model. This process invites adversaries to manipulate the training data so that the(More)
Using statistical machine learning for making security decisions introduces new vulnerabilities in large scale systems. This paper shows how an adversary can exploit statistical machine learning, as used in the SpamBayes spam filter, to render it useless—even if the adversary’s access is limited to only 1% of the training messages. We further demonstrate a(More)
Many researchers have applied statistical analysis techniques to email for classification purposes, such as identifying spam messages. Such approaches can be highly effective, however many examine incoming email exclusively — which does not provide detailed information about an individual user’s behavior. Only by analyzing outgoing messages can a user’s(More)