Toward Adversarial Online Learning and the Science of Deceptive Machines

Intelligent systems rely on pattern recognition and signaturebasedapproaches for a wide range of sensors enhancing situationalawareness. For example, autonomous systems dependon environmental sensors to perform their tasks and securesystems depend on anomaly detection methods. The availabilityof lar...

Full description

Saved in:
Bibliographic Details
Main Author: Abramson,Myriam
Format: Report
Language:English
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Abramson,Myriam
description Intelligent systems rely on pattern recognition and signaturebasedapproaches for a wide range of sensors enhancing situationalawareness. For example, autonomous systems dependon environmental sensors to perform their tasks and securesystems depend on anomaly detection methods. The availabilityof large amount of data requires the processing of datain a streaming fashion with online algorithms. Yet, just asonline learning can enhance adaptability to a non-stationaryenvironment, it introduces vulnerabilities that can be manipulatedby adversaries to achieve their goals while evadingdetection. Although human intelligence might have evolvedfrom social interactions, machine intelligence has evolved asa human intelligence artifact and been kept isolated to avoidethical dilemmas. As our adversaries become sophisticated,it might be time to revisit this question and examine how wecan combine online learning and reasoning leading to the scienceof deceptive and counter-deceptive machines. AAAI Fall Symposium , 12 Nov 2015, 14 Nov 2015,
format report
fullrecord <record><control><sourceid>dtic_1RU</sourceid><recordid>TN_cdi_dtic_stinet_AD1024327</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>AD1024327</sourcerecordid><originalsourceid>FETCH-dtic_stinet_AD10243273</originalsourceid><addsrcrecordid>eNrjZPAIyS9PLEpRcEwpSy0qTizKTMxR8M_LycxLVfBJTSzKy8xLV0jMS1EoyUhVCE7OTM1LTlXIT1NwSU1OLSjJLEtV8E1MzgCqLuZhYE1LzClO5YXS3Awybq4hzh66KSWZyfHFJUA1JfGOLoYGRibGRubGBKQBSHQwhw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>report</recordtype></control><display><type>report</type><title>Toward Adversarial Online Learning and the Science of Deceptive Machines</title><source>DTIC Technical Reports</source><creator>Abramson,Myriam</creator><creatorcontrib>Abramson,Myriam ; Naval Research Laboratory Washington United States</creatorcontrib><description>Intelligent systems rely on pattern recognition and signaturebasedapproaches for a wide range of sensors enhancing situationalawareness. For example, autonomous systems dependon environmental sensors to perform their tasks and securesystems depend on anomaly detection methods. The availabilityof large amount of data requires the processing of datain a streaming fashion with online algorithms. Yet, just asonline learning can enhance adaptability to a non-stationaryenvironment, it introduces vulnerabilities that can be manipulatedby adversaries to achieve their goals while evadingdetection. Although human intelligence might have evolvedfrom social interactions, machine intelligence has evolved asa human intelligence artifact and been kept isolated to avoidethical dilemmas. As our adversaries become sophisticated,it might be time to revisit this question and examine how wecan combine online learning and reasoning leading to the scienceof deceptive and counter-deceptive machines. AAAI Fall Symposium , 12 Nov 2015, 14 Nov 2015,</description><language>eng</language><creationdate>2015</creationdate><rights>Approved For Public Release</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,780,885,27567,27568</link.rule.ids><linktorsrc>$$Uhttps://apps.dtic.mil/sti/citations/AD1024327$$EView_record_in_DTIC$$FView_record_in_$$GDTIC$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Abramson,Myriam</creatorcontrib><creatorcontrib>Naval Research Laboratory Washington United States</creatorcontrib><title>Toward Adversarial Online Learning and the Science of Deceptive Machines</title><description>Intelligent systems rely on pattern recognition and signaturebasedapproaches for a wide range of sensors enhancing situationalawareness. For example, autonomous systems dependon environmental sensors to perform their tasks and securesystems depend on anomaly detection methods. The availabilityof large amount of data requires the processing of datain a streaming fashion with online algorithms. Yet, just asonline learning can enhance adaptability to a non-stationaryenvironment, it introduces vulnerabilities that can be manipulatedby adversaries to achieve their goals while evadingdetection. Although human intelligence might have evolvedfrom social interactions, machine intelligence has evolved asa human intelligence artifact and been kept isolated to avoidethical dilemmas. As our adversaries become sophisticated,it might be time to revisit this question and examine how wecan combine online learning and reasoning leading to the scienceof deceptive and counter-deceptive machines. AAAI Fall Symposium , 12 Nov 2015, 14 Nov 2015,</description><fulltext>true</fulltext><rsrctype>report</rsrctype><creationdate>2015</creationdate><recordtype>report</recordtype><sourceid>1RU</sourceid><recordid>eNrjZPAIyS9PLEpRcEwpSy0qTizKTMxR8M_LycxLVfBJTSzKy8xLV0jMS1EoyUhVCE7OTM1LTlXIT1NwSU1OLSjJLEtV8E1MzgCqLuZhYE1LzClO5YXS3Awybq4hzh66KSWZyfHFJUA1JfGOLoYGRibGRubGBKQBSHQwhw</recordid><startdate>20151114</startdate><enddate>20151114</enddate><creator>Abramson,Myriam</creator><scope>1RU</scope><scope>BHM</scope></search><sort><creationdate>20151114</creationdate><title>Toward Adversarial Online Learning and the Science of Deceptive Machines</title><author>Abramson,Myriam</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-dtic_stinet_AD10243273</frbrgroupid><rsrctype>reports</rsrctype><prefilter>reports</prefilter><language>eng</language><creationdate>2015</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Abramson,Myriam</creatorcontrib><creatorcontrib>Naval Research Laboratory Washington United States</creatorcontrib><collection>DTIC Technical Reports</collection><collection>DTIC STINET</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Abramson,Myriam</au><aucorp>Naval Research Laboratory Washington United States</aucorp><format>book</format><genre>unknown</genre><ristype>RPRT</ristype><btitle>Toward Adversarial Online Learning and the Science of Deceptive Machines</btitle><date>2015-11-14</date><risdate>2015</risdate><abstract>Intelligent systems rely on pattern recognition and signaturebasedapproaches for a wide range of sensors enhancing situationalawareness. For example, autonomous systems dependon environmental sensors to perform their tasks and securesystems depend on anomaly detection methods. The availabilityof large amount of data requires the processing of datain a streaming fashion with online algorithms. Yet, just asonline learning can enhance adaptability to a non-stationaryenvironment, it introduces vulnerabilities that can be manipulatedby adversaries to achieve their goals while evadingdetection. Although human intelligence might have evolvedfrom social interactions, machine intelligence has evolved asa human intelligence artifact and been kept isolated to avoidethical dilemmas. As our adversaries become sophisticated,it might be time to revisit this question and examine how wecan combine online learning and reasoning leading to the scienceof deceptive and counter-deceptive machines. AAAI Fall Symposium , 12 Nov 2015, 14 Nov 2015,</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_dtic_stinet_AD1024327
source DTIC Technical Reports
title Toward Adversarial Online Learning and the Science of Deceptive Machines
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T14%3A21%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-dtic_1RU&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=unknown&rft.btitle=Toward%20Adversarial%20Online%20Learning%20and%20the%20Science%20of%20Deceptive%20Machines&rft.au=Abramson,Myriam&rft.aucorp=Naval%20Research%20Laboratory%20Washington%20United%20States&rft.date=2015-11-14&rft_id=info:doi/&rft_dat=%3Cdtic_1RU%3EAD1024327%3C/dtic_1RU%3E%3Cgrp_id%3Ecdi_FETCH-dtic_stinet_AD10243273%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true