{"623785":{"#nid":"623785","#data":{"type":"news","title":"MLsploit Tackles Machine Learning Security with a Cloud-based Platform","body":[{"value":"\u003Cp\u003EMachine Learning (ML) algorithms are pervasive in our daily lives and are the basis for everything from suggestions on streaming platforms to fraud detection services, yet recent research has found that they are highly vulnerable to attacks.\u0026nbsp;These attacks come in many forms, including bypassing Android and Linux malware detection, and attacking deep learning models for image misclassification and objection detection.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETo patch these vulnerabilities and increase security for safety-critical applications, researchers at Georgia Tech and Intel have teamed up to create\u0026nbsp;\u003Ca href=\u0022https:\/\/mlsploit.github.io\/\u0022\u003EMLsploit\u003C\/a\u003E. It is\u0026nbsp;the first user-friendly, cloud-based framework that enables researchers and developers to rapidly evaluate and compare state-of-the-art adversarial attacks and defenses for ML models.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EWhat Does MLsploit Do?\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMLsploit\u0026rsquo;s web interface is open-source and allows researchers to quickly perform experiments on attack and defense algorithms by easily adjusting their parameters. Once tests are finished, the user may store the results in the framework to serve as a growing database for future adversarial ML research to build on.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;MLsploit is unique in that it is a collection and repository in the specific space of adversarial ML,\u0026rdquo; said\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cse.gatech.edu\/\u0022\u003ESchool of Computational Science and Engineering\u003C\/a\u003E\u0026nbsp;Ph.D. student\u0026nbsp;\u003Cstrong\u003ENilaksh Das\u003C\/strong\u003E, a primary student investigator of the project.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMLsploit researchers built the tool as the springboard for students and researchers in adversarial ML, deep learning practitioners in industry who want to perform in-depth experimentation on a new model before rolling it out for private or public use.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Ultimately, our goal is for MLsploit to become a collection of all the literature in the adversarial ML space,\u0026rdquo; he said.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EHow Does MLsploit Work?\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMLsploit was built to be modular so that users can easily integrate their own work into the framework.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMLsploit provides the user the web-user interface and the back-end computation engine. Then, the user can upload their own modules or functions. Once these are created, they can be used in conjunction with the whole MLsploit framework.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe tool was developed at the\u0026nbsp;\u003Ca href=\u0022http:\/\/istc-arsa.iisp.gatech.edu\/\u0022\u003EIntel\u0026reg; Science \u0026amp; Technology Center for Adversary-Resilient Security Analytics\u003C\/a\u003E\u0026nbsp;(ISTC-ARSA) housed at Tech. The center specializes in\u0026nbsp;identifying vulnerabilities of ML algorithms and developing new security approaches to improve the resilience of ML applications.The project represents a culmination of the last three years of research in the center.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMLsploit was first presented at\u0026nbsp;\u003Ca href=\u0022https:\/\/www.blackhat.com\/asia-19\/\u0022\u003EBlack Hat Asia 2019\u003C\/a\u003E\u0026nbsp;and will be presented again as a Project Showcase at the\u0026nbsp;\u003Ca href=\u0022https:\/\/www.kdd.org\/kdd2019\/\u0022\u003E25\u003Csup\u003Eth\u0026nbsp;\u003C\/sup\u003EACM SIGKDD Conference on Knowledge Discovery and Data Mining\u003C\/a\u003E.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAn extended abstract and complete listing of co-authors for the paper can be found\u0026nbsp;\u003Ca href=\u0022https:\/\/istc-arsa.iisp.gatech.edu\/mlsploit-extended-abstract-to-appear-in-kdd-2019.html\u0022\u003Ehere\u003C\/a\u003E.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Georgia Tech and Intel researchers launch MLsploit, a cloud-based platform for researching adversarial Machine Learning."}],"uid":"34540","created_gmt":"2019-07-29 20:45:59","changed_gmt":"2022-05-26 17:09:36","author":"Kristen Perez","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2019-07-29T00:00:00-04:00","iso_date":"2019-07-29T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"623781":{"id":"623781","type":"image","title":"MLsploit","body":null,"created":"1564432161","gmt_created":"2019-07-29 20:29:21","changed":"1564432161","gmt_changed":"2019-07-29 20:29:21","alt":"A diagram showing how MLsploit feeds algorithms through its framework","file":{"fid":"237584","name":"Screen Shot 2019-07-22 at 5.16.18 PM.png","image_path":"\/sites\/default\/files\/images\/Screen%20Shot%202019-07-22%20at%205.16.18%20PM.png","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/Screen%20Shot%202019-07-22%20at%205.16.18%20PM.png","mime":"image\/png","size":65861,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/Screen%20Shot%202019-07-22%20at%205.16.18%20PM.png?itok=0TYb1DPF"}}},"media_ids":["623781"],"groups":[],"categories":[{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"},{"id":"135","name":"Research"}],"keywords":[{"id":"181831","name":"MLsploit"},{"id":"83261","name":"Polo Chau"},{"id":"181832","name":"Nilaksh Das"},{"id":"181833","name":"cse-cyber"},{"id":"181220","name":"cse-ml"}],"core_research_areas":[{"id":"145171","name":"Cybersecurity"},{"id":"39501","name":"People and Technology"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EKristen Perez - Communications Officer\u003C\/p\u003E","format":"limited_html"}],"email":["kristen.perez@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}