Meta tags:

Headings (most frequently used words):

workshop, for, multimedia, alan, yuille, li, chen, liu, 1st, international, on, adversarial, learning, overview, important, dates, schedule, keynote, speakers, call, papers, organizers, paper, submission, program, committee, related, workshops, sponsors, at, acm, 2021, xiaochun, cao, bo, tom, goldstein, baoyuan, wu, pin, yu, boqing, gong, cihang, xie, dawn, song, dacheng, tao, anima, anandkumar, xianglong, aishan, xinyun, yingwei, chaowei, xiao, xun, yang,

Text of the page (most frequently used words):
university (19), #learning (18), adversarial (16), workshop (11), deep (11), for (9), systems (9), and (9), the (9), multimedia (8), beihang (6), 2021 (5), robustness (5), papers (5), research (5), machine (4), computer (4), vision (4), chen (3), liu (3), world (3), acm (3), pages (3), johns (3), hopkins (3), fields (3), that (3), examples (3), model (3), any (2), further (2), yingwei (2), xinyun (2), aishan (2), real (2), xie (2), tao (2), gong (2), submitted (2), format (2), must (2), template (2), may (2), references (2), https (2), submission (2), berkeley (2), california (2), alan (2), yuille (2), academy (2), has (2), achieved (2), significant (2), success (2), however (2), also (2), shows (2), highly (2), vulnerable (2), explainable (2), improving (2), understanding (2), robust (2), attacks (2), call (2), chinese (2), speakers (2), schedule (2), dates (2), acoustics (2), are (2), applications (2), focus (2), home (2), questions, you, can, contact, sponsors, online, challenges, cvpr, uncertainty, icml, iccv, security, safety, iclr, related, workshops, tbd, sun, austin, shiyu, tang, huiyuan, cambridge, yuqing, tianlin, nanyang, technological, zhuozhuo, sydney, renshuai, xiaohui, zeng, toronto, ruihao, sensetime, jiakai, wang, program, committee, pdf, use, article, please, remember, add, concepts, keywords, stated, cfp, two, additional, added, reference, only, contain, overlength, will, rejected, without, review, cmt3, microsoft, com, advm2021, site, length, www, org, publications, proceedings, paper, national, singapore, xun, yang, nvidia, arizona, state, chaowei, xiao, xianglong, institute, technology, anima, anandkumar, explore, dacheng, dawn, song, organizers, invite, submissions, aspect, topics, include, but, not, limited, generalization, performance, out, distribution, samples, vulnerabilities, benchmark, evaluating, training, techniques, building, architectures, against, attacking, santa, cruz, cihang, google, boqing, ibm, pin, hongkong, shenzhen, baoyuan, maryland, tom, goldstein, illinois, urbana, champaign, sciences, xiaochun, cao, keynote, important, involving, natural, language, processing, they, extensive, works, have, demonstrated, could, easily, fool, neural, networks, wrong, predictions, threatening, practical, both, digital, physical, though, challenging, discovering, harnessing, beneficial, diagnosing, blind, spots, well, practice, this, aim, bring, together, researchers, from, discuss, recent, future, directions, models, with, particular, including, etc, far, know, first, which, great, significance, overview, 1st, international, people, advm,

Text of the page (random words):
home advm workshop home dates speakers call for papers people schedule 1st international workshop on adversarial learning for multimedia workshop at acm multimedia 2021 overview deep learning has achieved significant success in multimedia fields involving computer vision natural language processing and acoustics however research in adversarial learning also shows that they are highly vulnerable to adversarial examples extensive works have demonstrated that adversarial examples could easily fool deep neural networks to wrong predictions threatening practical deep learning applications in both digital and physical world though challenging discovering and harnessing adversarial attacks is beneficial for diagnosing model blind spots and further understanding as well as improving multimedia systems in practice in this workshop we aim to bring together researchers from the fields of adversarial machine learning model robustness and explainable ai to discuss recent research and future directions for adversarial robustness of deep learning models with a particular focus on multimedia applications including computer vision acoustics etc as far as we know we are the first workshop to focus on adversarial learning of multimedia deep learning systems which is of great significance important dates workshop schedule keynote speakers alan yuille johns hopkins university xiaochun cao chinese academy of sciences bo li university of illinois at urbana champaign tom goldstein university of maryland baoyuan wu the chinese university of hongkong shenzhen pin yu chen ibm boqing gong google cihang xie university of california santa cruz call for papers deep learning has achieved significant success in multimedia fields however research in adversarial learning also shows that it is highly vulnerable to adversarial examples we invite submissions on any aspect of adversarial machine learning in multimedia deep learning systems topics include but not limited to adversarial attacking deep learning systems robust architectures against adversarial attacks training techniques for building robust deep learning systems benchmark for evaluating model robustness understanding the adversarial vulnerabilities of deep learning systems improving generalization performance of computer vision systems to out of distribution samples explainable ai organizers dawn song uc berkeley dacheng tao jd explore academy alan yuille johns hopkins university anima anandkumar california institute of technology xianglong liu beihang university aishan liu beihang university xinyun chen uc berkeley yingwei li johns hopkins university chaowei xiao nvidia research arizona state university xun yang national university of singapore paper submission format submitted papers pdf format must use the acm article template https www acm org publications proceedings template please remember to add concepts and keywords length as stated in the cfp submitted papers may be 6 to 8 pages up to two additional pages may be added for references the reference pages must only contain references overlength papers will be rejected without review submission site https cmt3 research microsoft com advm2021 program committee jiakai wang beihang university ruihao gong sensetime xiaohui zeng university of toronto renshuai tao beihang university zhuozhuo tu the university of sydney tianlin li nanyang technological university yuqing ma beihang university huiyuan xie university of cambridge shiyu tang beihang university bo sun ut austin tbd related workshops security and safety in machine learning systems workshop at iclr 2021 adversarial robustness in the real world workshop at iccv 2021 uncertainty robustness in deep learning workshop at icml 2021 workshop on adversarial machine learning in real world computer vision systems and online challenges workshop at cvpr 2021 sponsors for any further questions you can contact aishan liu xinyun chen or yingwei li