Adversarial Active Learning

Brad Miller, Alex Kantchelian, Sadia Afroz, Rekha Bachwani, Edwin Dauber, Ling Huang, Michael Carl Tschantz, Anthony D. Joseph, J.D. Tygar
<span title="">2014</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rau5643b7ncwvh74y6p64hntle" style="color: black;">Proceedings of the 2014 Workshop on Artificial Intelligent and Security Workshop - AISec &#39;14</a> </i> &nbsp;
Active learning is an area of machine learning examining strategies for allocation of finite resources, particularly human labeling efforts and to an extent feature extraction, in situations where available data exceeds available resources. In this open problem paper, we motivate the necessity of active learning in the security domain, identify problems caused by the application of present active learning techniques in adversarial settings, and propose a framework for experimentation and
more &raquo; ... ntation of active learning systems in adversarial contexts. More than other contexts, adversarial contexts particularly need active learning as ongoing attempts to evade and confuse classifiers necessitate constant generation of labels for new content to keep pace with adversarial activity. Just as traditional machine learning algorithms are vulnerable to adversarial manipulation, we discuss assumptions specific to active learning that introduce additional vulnerabilities, as well as present vulnerabilities that are amplified in the active learning setting. Lastly, we present a software architecture, Security-oriented Active Learning Testbed (SALT), for the research and implementation of active learning applications in adversarial contexts.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2666652.2666656">doi:10.1145/2666652.2666656</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ccs/MillerKABDHTJT14.html">dblp:conf/ccs/MillerKABDHTJT14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pperfvpyvnbh5kkpwge2zk4b4u">fatcat:pperfvpyvnbh5kkpwge2zk4b4u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150201002527/http://www.cs.berkeley.edu:80/~bmiller1/resources/papers/aisec2014.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f0/6c/f06c15f85f9b697fa621eb3272c0defbbeab9338.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2666652.2666656"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>