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

Headings (most frequently used words):

papers, committee, iclr, 2022, workshop, on, socially, responsible, machine, learning, srml, accepted, schedule, invited, speakers, organizing, program, important, dates, call, for,

Text of the page (most frequently used words):
and (35), university (29), the (20), talk (14), from (13), 2022 (13), learning (12), for (11), models (10), are (9), invited (9), #machine (8), workshop (8), privacy (8), zhang (7), michigan (7), prof (7), that (6), socially (6), responsible (6), contributed (6), systems (5), with (5), submission (5), papers (5), aoe (5), deadline (5), liu (5), have (4), been (4), applications (4), data (4), vision (4), can (4), accepted (4), real (4), theoretical (4), fairness (4), huan (4), iclr (4), anywhere (4), earth (4), social (4), state (4), paper (4), virginia (4), nvidia (4), robust (4), many (3), tasks (3), recognition (3), well (3), language (3), societal (3), not (3), focus (3), problems (3), but (3), world (3), transparency (3), various (3), security (3), xiao (3), submissions (3), authors (3), will (3), using (3), https (3), research (3), april (3), other (3), understanding (3), trustworthy (3), robustness (3), ohio (3), ann (3), arbor (3), cmu (3), smith (3), networks (3), best (3), award (3), under (3), carnegie (3), mellon (3), used (2), ranging (2), decision (2), making (2), foundation (2), has (2), which (2), trained (2), work (2), while (2), there (2), impact (2), risks (2), they (2), our (2), studies (2), them (2), hard (2), mitigating (2), providing (2), most (2), interpretability (2), connections (2), this (2), aims (2), together (2), both (2), applied (2), researchers (2), communities (2), ethics (2), etc (2), dot (2), com (2), chaowei (2), pages (2), proceedings (2), format (2), double (2), blind (2), references (2), supplementary (2), material (2), cmt3 (2), notification (2), camera (2), ready (2), poster (2), quality (2), impacts (2), bias (2), exhibit (2), discrimination (2), biases (2), existing (2), recent (2), day (2), hongyang (2), waterloo (2), xinchen (2), yan (2), xie (2), jiachen (2), sun (2), maryland (2), park (2), berkeley (2), committee (2), stanford (2), georgia (2), tech (2), diyi (2), yang (2), apoorva (2), sharma (2), neil (2), gong (2), judy (2), hoffman (2), anqi (2), aleksander (2), mądry (2), ziwei (2), quantum (2), non (2), lipschitz (2), winner (2), provably (2), fair (2), federated (2), via (2), bounded (2), group (2), loss (2), pre (2), break (2), modelnet40 (2), benchmark (2), point (2), cloud (2), corruption (2), domain (2), time (2), zone (2), information (2), such (2), increasingly, automated, resume, screening, pretrial, release, tool, safety, critical, face, financial, analytics, autonomous, driving, recently, concept, received, significant, attention, community, refers, rise, bert, gpt, large, scale, surprisingly, wide, range, downstream, opportunities, regarding, capabilities, robotics, reasoning, human, interaction, law, healthcare, education, transportation, inequity, misuse, economic, environmental, legal, ethical, considerations, concerns, incurred, inflict, harm, developed, care, documented, winners, although, extensive, conducted, increase, trust, either, defined, enable, nice, tractability, mathematical, perspective, adapted, mainly, without, justifications, moreover, separately, among, less, explored, bring, please, email, xiaocw, umich, edu, issues, contact, welcome, excluding, appendix, available, allow, unlimited, number, reviewers, required, review, unless, indicated, provide, pdfs, all, archival, manage, iclrsrml, github, style, files, microsoft, iclrsrml2022, server, mar, sent, feb, reviewing, performed, criteria, include, relevance, methodology, experiments, novelty, studying, may, inherently, cause, undesired, harms, trade, offs, costs, achieving, different, goals, reality, insights, about, how, automatically, detect, verify, explain, mitigate, potential, possibility, advancements, inform, practice, guidelines, deploying, art, their, usage, intersection, aspects, invite, any, aspect, responsibility, trustworthiness, includes, limited, call, important, dates, xinwei, zhao, drexel, waymo, chulin, illinois, urbana, champaign, chang, columbia, rajkumar, theagarajan, california, riverside, anshuman, suri, akshayvarun, subramanya, umbc, gaurang, sriramanan, college, aniruddha, saha, baltimore, county, nataniel, ruiz, boston, maura, pintor, cagliari, won, swetasudha, panda, oracle, labs, xinlei, pan, parinaz, naghizadeh, xingjun, deakin, jia, adam, kortylewski, max, planck, institute, informatics, mohammad, mahdi, khalili, delaware, kun, jin, lifeng, huang, sunyat, sen, junheng, hao, ucla, yulong, cao, chirag, agarwal, adobe, zelun, luo, program, caltech, anima, anandkumar, dawn, song, zico, kolter, uiuc, austin, yuke, zhu, beidi, chen, ucsc, cihang, xueru, organizing, duke, johns, hopkins, angie, mit, nanyang, technological, speakers, gathertown, session, link, gather, town, owwngoinbf9nm2gr, iclr2022srml, incentive, mechanisms, strategic, differential, amplification, inspired, algorithms, power, abstention, driven, debiasing, neural, differentiable, classification, parity, proxies, dialect, inclusive, natural, marco, pavone, runtime, introspection, dnns, out, distribution, detection, meets, heterogeneity, secure, self, supervised, lunch, uncertainty, calibration, cross, transfer, coffee, matters, rethinking, generalization, architectures, modalities, beyond, opening, remarks, eastern, utc, schedule, shengyuan, steven, qingzhao, bhavya, kailkhura, lawrence, livermore, national, laboratory, zhiding, zhuoqing, morley, mao, list, high, build, bringing, future, directions, unreliable, unpredictable, shift, input, variations, life, scenarios, make, justify, predictions, lack, explanation, vulnerable, attacks, deceive, leak, sensitive, training, medical, records, personal, identifiable, pii, inherit, against, already, disadvantaged, marginalized, groups, bipoc, lgbtq, abstract, virtual, only, located, location, friday, date, srml,

Text of the page (random words):
iclr 2022 workshop on socially responsible machine learning iclr 2022 workshop on socially responsible machine learning srml date april 29 2022 friday location virtual only co located with iclr 2022 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 face recognition financial analytics and autonomous driving recently the concept of foundation models has received significant attention in the ml community which refers to the rise of models e g bert gpt 3 that are trained on large scale data and work surprisingly well in a wide range of downstream tasks while there are many opportunities regarding foundation models ranging from capabilities e g language vision robotics reasoning human interaction applications e g law healthcare education transportation and societal impact e g inequity misuse economic and environmental impact legal and ethical considerations concerns and risks have been incurred that the models can inflict harm if they are not developed or used with care it has been well documented that ml models can inherit pre existing social biases and exhibit discrimination against already disadvantaged or marginalized social groups such as bipoc and lgbtq be vulnerable to security and or privacy attacks that deceive the models and leak the sensitive information in training data such as medical records and personal identifiable information pii make hard to justify predictions with a lack of transparency and explanation be unreliable and unpredictable under domain shift or other input variations in real life scenarios 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 with a focus on recent research and future directions for socially responsible machine learning problems in real world systems accepted papers our workshop accepted 28 high quality papers list of accepted papers our best paper award winners are modelnet40 c a robustness benchmark for 3d point cloud recognition under corruption jiachen sun university of michigan qingzhao zhang university of michigan ann arbor bhavya kailkhura lawrence livermore national laboratory zhiding yu nvidia zhuoqing morley mao university of michigan provably fair federated learning via bounded group loss shengyuan hu carnegie mellon university steven wu carnegie mellon university virginia smith carnegie mellon university schedule workshop day 04 29 2022 time zone us eastern time zone utc 05 00 09 20 09 40 opening remarks prof bo li 09 40 10 20 invited talk from prof ziwei liu rethinking generalization in vision models architectures modalities and beyond 10 20 11 00 invited talk from prof aleksander mądry data matters coffee break 11 10 11 50 invited talk from prof anqi liu uncertainty calibration for robust cross domain transfer in vision and language tasks 11 50 12 30 invited talk from prof judy hoffman understanding and mitigating bias in vision models lunch 13 30 13 50 contributed talk 1 modelnet40 c a robustness benchmark for 3d point cloud recognition under corruption best paper award winner 13 50 14 30 invited talk from neil gong secure self supervised learning 14 30 15 10 invited talk from virginia smith privacy meets heterogeneity break 15 20 16 00 invited talk from prof marco pavone and dr apoorva sharma runtime introspection of pre trained dnns for out of distribution detection 16 00 16 40 invited talk from prof diyi yang dialect inclusive and robust natural language understanding 16 40 17 00 contributed talk 2 provably fair federated learning via bounded group loss best paper award winner 17 00 17 20 contributed talk 3 debiasing neural networks using differentiable classification parity proxies 17 20 17 40 contributed talk 4 can non lipschitz networks be robust the power of abstention and data driven decision making for robust non lipschitz networks 17 40 18 00 contributed talk 5 differential privacy amplification in quantum and quantum inspired algorithms 18 00 18 20 contributed talk 6 incentive mechanisms in strategic learning 19 00 20 00 gathertown poster session link https gather town owwngoinbf9nm2gr iclr2022srml invited speakers ziwei liu nanyang technological university aleksander mądry mit anqi angie liu johns hopkins university judy hoffman georgia tech neil gong duke university virginia smith cmu apoorva sharma stanford diyi yang georgia tech organizing committee chaowei xiao nvidia huan zhang cmu xueru zhang ohio state university hongyang zhang waterloo cihang xie ucsc beidi chen stanford xinchen yan yuke zhu ut austin nvidia bo li uiuc zico kolter cmu dawn song uc berkeley anima anandkumar caltech nvidia program committee zelun luo chirag agarwal adobe yulong cao university of michigan ann arbor junheng hao ucla lifeng huang sunyat sen university kun jin university of michigan ann arbor mohammad mahdi khalili university of delaware adam kortylewski max planck institute for informatics jia liu the ohio state university xingjun ma deakin university parinaz naghizadeh ohio state university xinlei pan uc berkeley swetasudha panda oracle labs won park university of michigan maura pintor university of cagliari nataniel ruiz boston university aniruddha saha university of maryland baltimore county gaurang sriramanan university of maryland college park akshayvarun subramanya umbc jiachen sun university of michigan anshuman suri university of virginia rajkumar theagarajan university of california riverside chang xiao columbia university chulin xie university of illinois at urbana champaign xinchen yan waymo hongyang zhang university of waterloo xinwei zhao drexel university important dates workshop paper submission deadline 02 25 2022 aoe notification to authors 03 25 2022 camera ready deadline 04 10 2022 workshop day 04 29 2022 call for papers although extensive studies have been conducted to increase trust in ml many of them either focus on well defined problems that enable nice tractability from a mathematical perspective but are hard to be adapted to real world systems or they mainly focus on mitigating risks in real world applications without providing theoretical justifications moreover most work studies fairness privacy transparency and interpretability separately while the connections among them are less explored this workshop aims to bring together both theoretical and applied researchers from various communities e g machine learning fairness ethics security privacy etc we invite submissions on any aspect of the social responsibility and trustworthiness of machine learning which includes but not limited to the intersection of various aspects of socially responsible and trustworthy ml fairness transparency interpretability privacy robustness the state of the art research of socially responsible and trustworthy ml and their usage in applications the possibility of using the most recent theoretical advancements to inform practice guidelines for deploying socially responsible and trustworthy ml systems providing insights about how we can automatically detect verify explain and mitigate potential biases privacy or other societal problems in existing models understanding the trade offs or costs of achieving different goals in reality studying the social impacts of machine learning models that may inherently have bias exhibit discrimination or cause other undesired harms reviewing will be performed in double blind with criteria include a relevance b quality of the methodology and experiments c novelty d societal impacts poster deadline april 17 2022 anywhere on earth aoe camera ready deadline april 10 2022 anywhere on earth aoe submission deadline feb 25 2022 anywhere on earth aoe notification sent to authors mar 25 2022 anywhere on earth aoe submission server https cmt3 research microsoft com iclrsrml2022 submission format we welcome submissions up to 4 pages in iclr proceedings format double blind excluding references and appendix style files 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 iclrsrml github io there will be no archival proceedings we are using cmt3 to manage submissions contact please email chaowei xiao xiaocw at umich dot edu and huan zhang huan at huan zhang dot com for submission issues