Meta tags:
description=ICML Workshop on Security in Machine Learning;

Headings (most frequently used words):

committee, organizing, socially, responsible, machine, learning, schedule, senior, program, important, dates, call, for, papers,

Text of the page (most frequently used words):
university (29), the (24), and (20), #learning (14), talk (13), machine (12), for (9), invited (9), models (7), workshop (7), 2021 (7), will (6), with (6), socially (5), responsible (5), that (5), are (5), privacy (5), systems (5), contributed (5), michigan (5), bias (4), paper (4), not (4), papers (4), submission (4), can (4), this (4), stanford (4), zhang (4), liu (4), from (4), various (3), have (3), submissions (3), authors (3), all (3), accepted (3), social (3), problems (3), recent (3), trustworthy (3), state (3), research (3), fairness (3), transparency (3), security (3), update (3), deadline (3), ucla (3), chen (3), zhu (3), committee (3), been (3), example (2), recognition (2), financial (2), analytics (2), autonomous (2), perturbation (2), build (2), fair (2), pages (2), icml (2), proceedings (2), format (2), references (2), supplementary (2), material (2), but (2), https (2), icmlsrml2021 (2), cmt3 (2), understanding (2), different (2), how (2), biases (2), existing (2), applications (2), trust (2), interpretability (2), robustness (2), ethics (2), virtual (2), july (2), anywhere (2), earth (2), aoe (2), notification (2), sent (2), zelun (2), luo (2), ann (2), arbor (2), sun (2), xueru (2), zhao (2), yan (2), wang (2), ohio (2), xie (2), illinois (2), urbana (2), champaign (2), maryland (2), virginia (2), anima (2), anandkumar (2), organizing (2), information (2), nlp (2), societal (2), break (2), jun (2), uncertainty (2), change (2), adversarial (2), schedule (2), time (2), zone (2), together (2), communities (2), well (2), used (2), decision (2), making (2), commercial, face, products, were, shown, racial, gender, domains, such, vehicles, could, easily, misled, carefully, crafted, small, even, natural, therefore, essential, robust, private, transparent, interpretable, welcome, double, blind, excluding, appendix, available, allow, unlimited, number, reviewers, required, review, unless, indicated, provide, pdfs, github, there, archival, using, manage, style, files, explaining, impacts, tradeoffs, costs, achieving, goals, reality, providing, insights, about, automatically, detect, verify, explain, mitigate, potential, possibility, adopting, most, theory, inform, practice, guidelines, deploying, art, intersection, between, pillars, invite, includes, limited, any, aspect, relates, include, completely, details, later, microsoft, com, server, june, call, camera, ready, important, dates, zhiding, nvidia, yuzhe, yang, mit, yulong, cao, yizhou, yingwei, johns, hopkins, xinwei, drexel, xinlei, pan, berkeley, xingjun, deakin, xinchen, uber, atg, won, park, wenxiao, tsinghua, sunipa, dev, utah, sravanti, addepalli, indian, institute, science, rajkumar, theagarajan, california, riverside, parinaz, naghizadeh, nataniel, ruiz, boston, muhammad, awais, kyung, hee, mohammad, mahdi, khalili, delaware, maura, pintor, cagliari, kun, jin, kexin, rong, junheng, hao, juba, ziani, pennsylvania, josiah, wong, jiachen, jia, jamie, hayes, google, deepmind, huan, hongyang, ttic, chulin, chirag, agarwal, harvard, boxin, tech, anshuman, suri, aniruddha, saha, baltimore, county, alexandra, chouldechova, cmu, akshayvarun, subramanya, umbc, anqi, caltech, aishan, beihang, program, raquel, urtasun, dawn, song, mingyan, senior, xinyun, cihang, jieyu, chaowei, xiao, poster, sessions, gathertown, link, auditing, verified, deployment, under, semantic, specifications, fermi, empirical, risk, minimization, via, exponential, rényi, mutual, humans, advice, more, comes, analysis, human, interactions, yulia, tsvetkov, proactive, prevent, ethical, kai, wei, chang, language, generation, rewriting, gans, aaron, roth, better, estimates, prediction, api, shift, assessments, coming, lunch, nicolas, papernot, what, does, mean, tatsunori, hashimoto, noise, confounders, inherent, disagreements, coffee, pin, good, olga, russakovsky, revealing, quantifying, analyzing, mitigating, visual, understand, benchmark, deep, opening, remarks, found, here, tentative, subject, prior, eastern, utc, aims, connections, bringing, both, theoretical, applied, researchers, etc, focus, future, directions, machien, real, world, aim, bring, experts, attempt, highlight, work, area, clarify, foundations, make, hard, justify, predictions, lack, vulnerable, attacks, deceive, leak, training, data, sensitive, inherit, pre, exhibit, discrimination, against, already, disadvantaged, marginalized, groups, increasingly, many, ranging, automated, resume, screening, pretrial, release, tool, safety, critical, tasks, driving, while, hope, improve, accuracy, outcomes, these, concerns, incurred, they, inflict, harm, developed, care, has, documented, abstract, out, results, check, only, located, location, date, hosting, new, iclr, same, topic,

Text of the page (random words):
socially responsible machine learning socially responsible machine learning update we are hosting a new workshop on the iclr with the same topic date july 24 2021 location virtual only co located with icml 2021 update we ve sent out the results for the papers check all the accepted paper abstract machine learning ml systems have been increasingly used in many applications ranging from decision making systems e g automated resume screening and pretrial release tool to safety critical tasks e g financial analytics and autonomous driving while the hope is to improve decision making accuracy and societal outcomes with these ml models concerns have been incurred that they can inflict harm if not developed or used with care it has been well documented that ml models can inherit pre existing biases and exhibit discrimination against already disadvantaged or marginalized social groups be vulnerable to security and privacy attacks that deceive the models and leak the training data s sensitive information make hard to justify predictions with a lack of transparency for example various commercial face recognition products were shown to have racial gender bias in domains such as financial analytics and autonomous vehicles ml models could be easily misled by carefully crafted small perturbation or even natural perturbation therefore it is essential to build socially responsible machine learning models that are fair robust private transparent and interpretable this workshop aims to build connections by bringing together both theoretical and applied researchers from various communities e g machine learning fairness ethics security privacy etc this workshop will focus on recent research and future directions for socially responsible machien learning problems in real world machine learning systems we aim to bring together experts from different communities in an attempt to highlight recent work in this area as well as to clarify the foundations of socially responsible machine learning schedule the tentative schedule is subject to change prior to the workshop time zone us eastern time zone utc 05 00 accepted paper can be found here 8 45 9 00 anima anandkumar opening remarks 9 00 9 40 invited talk jun zhu understand and benchmark adversarial robustness of deep learning 9 40 10 20 invited talk olga russakovsky revealing quantifying analyzing and mitigating bias in visual recognition 10 20 11 00 invited talk pin yu chen adversarial machine learning for good coffee break 11 10 11 50 invited talk tatsunori hashimoto not all uncertainty is noise machine learning with confounders and inherent disagreements 11 50 12 30 invited talk nicolas papernot what does it mean for ml to be trustworthy lunch 13 30 13 50 contributed talk machine learning api shift assessments change is coming 13 50 14 30 invited talk aaron roth better estimates of prediction uncertainty 14 30 15 10 invited talk jun yan zhu understanding and rewriting gans break 15 20 16 00 invited talk kai wei chang societal bias in language generation 16 00 16 40 invited talk yulia tsvetkov proactive nlp how to prevent social and ethical problems in nlp systems 16 40 17 00 contributed talk do humans trust advice more if it comes from ai an analysis of human ai interactions 17 00 17 20 contributed talk fermi fair empirical risk minimization via exponential rényi mutual information 17 20 17 40 contributed talk auditing ai models for verified deployment under semantic specifications 18 00 19 00 poster sessions at gathertown link organizing committee chaowei xiao xueru zhang jieyu zhao cihang xie xinyun chen senior organizing committee anima anandkumar bo li mingyan liu dawn song raquel urtasun program committee zelun luo stanford university aishan liu beihang university anqi liu caltech akshayvarun subramanya umbc alexandra chouldechova cmu aniruddha saha university of maryland baltimore county anshuman suri university of virginia bo ji virginia tech boxin wang university of illinois at urbana champaign chen zhu university of maryland chirag agarwal harvard university chulin xie university of illinois at urbana champaign hongyang zhang ttic huan zhang ucla jamie hayes google deepmind jia liu ohio state university jiachen sun university of michigan josiah wong stanford university juba ziani university of pennsylvania junheng hao ucla kexin rong stanford university kun jin university of michigan ann arbor maura pintor university of cagliari mohammad mahdi khalili university of delaware muhammad awais kyung hee university nataniel ruiz boston university parinaz naghizadeh ohio state university rajkumar theagarajan university of california riverside sravanti addepalli indian institute of science sunipa dev university of utah wenxiao wang tsinghua university won park university of michigan xinchen yan uber atg xingjun ma deakin university xinlei pan uc berkeley xinwei zhao drexel university xueru zhang university of michigan yingwei li johns hopkins university yizhou sun ucla yulong cao university of michigan ann arbor yuzhe yang mit zelun luo stanford university zhiding yu nvidia important dates workshop paper submission deadline 06 10 2021 notification to authors 07 10 2021 camera ready deadline 07 15 2021 call for papers submission deadline june 10 2021 anywhere on earth aoe notification sent to authors july 10 2021 anywhere on earth aoe submission server https cmt3 research microsoft com icmlsrml2021 the workshop will include contributed papers the workshop will be completely virtual we will update the details later we invite submissions on any aspect of machine learning that relates to fairness ethics transparency interpretability security and privacy this includes but is not limited to the intersection between various pillars of trust fairness transparency interpretability privacy robustness the state of the art research of trustworthy ml in applications the possibility of adopting the most recent theory to inform practice guidelines for deploying trustworthy ml systems providing insights about how we can automatically detect verify explain and mitigate potential biases or privacy problems in existing models understanding the tradeoffs or costs of achieving different goals in reality explaining the social impacts of the machine learning bias submission format we welcome submissions up to 4 pages in icml proceedings format double blind excluding references and appendix style files and an example paper are available we allow an unlimited number of pages for references and supplementary material but reviewers are not required to review the supplementary material unless indicated by the authors we will provide pdfs of all accepted papers on https icmlsrml2021 github io there will be no archival proceedings we are using cmt3 to manage submissions