{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:27:27Z","timestamp":1764588447468,"version":"3.37.3"},"reference-count":130,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003626","name":"Defense Acquisition Program Administration (DAPA)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003626","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005073","name":"Agency for Defense Development (ADD)","doi-asserted-by":"publisher","award":["UD190031RD"],"award-info":[{"award-number":["UD190031RD"]}],"id":[{"id":"10.13039\/501100005073","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/cvpr52729.2023.01555","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:30:52Z","timestamp":1692725452000},"page":"16206-16218","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck"],"prefix":"10.1109","author":[{"given":"Jongheon","family":"Jeong","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sihyun","family":"Yu","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hankook","family":"Lee","sequence":"additional","affiliation":[{"name":"LG AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwoo","family":"Shin","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref57","first-page":"2649","article-title":"Disentangling by factorising","author":"kim","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref56","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"khosla","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref59","article-title":"Glow: Generative flow with invertible 1×1 convolutions","volume":"31","author":"kingma","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"ICLR (Poster)"},{"key":"ref53","first-page":"12104","article-title":"Training generative adversarial networks with limited data","volume":"33","author":"karras","year":"2020","journal-title":"Advances in neural information processing systems"},{"journal-title":"Transfer of Adversarial Robustness Between Perturbation Types","year":"2019","author":"kang","key":"ref52"},{"key":"ref55","first-page":"8110","article-title":"Analyzing and improving the image quality of StyleGAN","author":"karras","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref51","article-title":"Training GANs with stronger augmentations via contrastive discriminator","author":"jeong","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref50","first-page":"10558","article-title":"Consistency regularization for certified robustness of smoothed classifiers","volume":"33","author":"jeong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref46","article-title":"Excessive invariance causes adversarial vulnerability","author":"jacobsen","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref45","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"journal-title":"Discovery and separation of features for invariant representation learning","year":"2019","author":"jaiswal","key":"ref48"},{"key":"ref47","article-title":"i-RevNet: Deep invertible networks","author":"jacobsen","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref42","article-title":"Imagen video: High definition video generation with diffusion models","author":"ho","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref41","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref44","article-title":"Adversarial examples are not bugs, they are features","volume":"32","author":"ilyas","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref43","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref49","article-title":"Unsupervised adversarial invariance","volume":"31","author":"jaiswal","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Better plain ViT baselines for ImageNet-1k","author":"beyer","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.6.1129"},{"key":"ref9","first-page":"1059","article-title":"High-performance large-scale image recognition without normalization","author":"brock","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref4","first-page":"7828","article-title":"Training normalizing flows with the information bottleneck for competitive generative classification","volume":"33","author":"ardizzone","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"A contrastive learning approach for training variational autoencoder priors","volume":"34","author":"aneja","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"573","article-title":"Invertible residual networks","author":"behrmann","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref5","first-page":"274","article-title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","author":"athalye","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning Volume 80 of Proceedings of Machine Learning Research"},{"key":"ref100","article-title":"Input complexity and out-of-distribution detection with likelihood-based generative models","author":"serra","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref101","article-title":"Denoising diffusion implicit models","author":"song","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref40","first-page":"16783","article-title":"PixMix: Dream-like pictures comprehensively improve safety measures","author":"hendrycks","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref35","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"hendrycks","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref37","article-title":"Deep anomaly detection with outlier exposure","author":"hendrycks","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref36","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"hendrycks","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref31","article-title":"Your classifier is secretly an energy based model and you should treat it like one","author":"grathwohl","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref30","article-title":"FFJORD: Free-form continuous dynamics for scalable reversible generative models","author":"grathwohl","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref39","article-title":"Aug-Mix: A simple method to improve robustness and uncertainty under data shift","author":"hendrycks","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref38","article-title":"Using self-supervised learning can improve model robustness and uncertainty","volume":"32","author":"hendrycks","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"International Conference on Learning Representations"},{"journal-title":"Density estimation using real nvp","year":"2016","author":"dinh","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref25","article-title":"Understanding the limitations of conditional generative models","author":"fetaya","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref20","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume":"34","author":"dai","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"A winning hand: Compressing deep networks can improve out-of-distribution robustness","volume":"34","author":"diffenderfer","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"CINIC-10 is not ImageNet or CIFAR-10","author":"darlow","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref27","article-title":"Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"geirhos","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref29","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref13","article-title":"Residual flows for invertible generative modeling","volume":"32","author":"chen","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Relevant sparse codes with variational information bottleneck","volume":"29","author":"chalk","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Very deep VAEs generalize autoregressive models and can outperform them on images","author":"child","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref128","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","author":"zhang","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref14","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning Proceedings of Machine Learning Research"},{"key":"ref129","first-page":"11298","article-title":"Perceptual generative autoencoders","author":"zhang","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref127","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"International Conference on Learning Representations"},{"journal-title":"On evaluating adversarial robustness","year":"2019","author":"carlini","key":"ref11"},{"key":"ref99","article-title":"Towards the first adversarially robust neural network model on MNIST","author":"schott","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref124","article-title":"Vector-quantized image modeling with improved VQGAN","author":"yu","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1488","DOI":"10.1109\/TIP.2011.2173206","article-title":"On the mathematical properties of the structural similarity index","volume":"21","author":"brunet","year":"2011","journal-title":"IEEE Transactions on Image Processing"},{"key":"ref98","article-title":"Projected GANs converge faster","author":"sauer","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref125","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","author":"yu","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref17","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","author":"cohen","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref16","article-title":"An empirical evaluation on robustness and uncertainty of regularization methods","author":"chun","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Diagnosing and enhancing VAE models","author":"dai","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00088"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17120"},{"key":"ref95","article-title":"Likelihood ratios for out-of-distribution detection","volume":"32","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref94","article-title":"Do CIFAR-10 classifiers generalize to CIFAR-10?","author":"recht","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref130","first-page":"7559","article-title":"Differentiable augmentation for data-efficient GAN training","volume":"33","author":"zhao","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref91","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref89","article-title":"Do deep generative models know what they don't know?","author":"nalisnick","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01571"},{"key":"ref88","article-title":"MNIST-C: A robustness benchmark for computer vision","author":"mu","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref87","first-page":"7721","article-title":"Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization","author":"miller","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref82","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref81","article-title":"Harder or different? a closer look at distribution shift in dataset reproduction","author":"lu","year":"2020","journal-title":"ICML Workshops Workshop on Uncertainty and Robustness in Deep Learning"},{"key":"ref84","first-page":"3481","article-title":"Which training methods for GANs do actually converge?","author":"mescheder","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref83","article-title":"Adversarial autoencoders","author":"makhzani","year":"2015","journal-title":"ArXiv Preprint"},{"journal-title":"The variational fair autoencoder","year":"2015","author":"louizos","key":"ref80"},{"key":"ref79","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"journal-title":"SGDR Stochastic gradient descent with warm restarts","year":"2016","author":"loshchilov","key":"ref78"},{"key":"ref109","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"tong","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref106","article-title":"The convex information bottleneck lagrangian","volume":"22","author":"thobaben","year":"2020","journal-title":"Entropy"},{"key":"ref107","first-page":"368","article-title":"The information bottleneck method","author":"tishby","year":"1999","journal-title":"proceedings of the 37-th Annual Allerton Conference on Communication Control and Computing"},{"key":"ref75","article-title":"Towards faster and stabilized GAN training for high-fidelity few-shot image synthesis","author":"liu","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"ref74","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"liang","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref105","first-page":"18583","article-title":"Measuring robustness to natural distribution shifts in image classification","volume":"33","author":"taori","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"journal-title":"Intriguing properties of neural networks","year":"2014","author":"szegedy","key":"ref102"},{"key":"ref76","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume":"33","author":"liu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref103","article-title":"CSI: Novelty detection via contrastive learning on distributionally shifted instances","author":"tack","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Concrete problems in AI safety","author":"amodei","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Deep variational information bottleneck","author":"alemi","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref71","article-title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","author":"lee","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref111","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00044"},{"key":"ref112","article-title":"Adversarial training and robustness for multiple perturbations","volume":"32","author":"tramer","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref73","first-page":"3763","article-title":"Robust inference via generative classifiers for handling noisy labels","author":"lee","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning volume 97 of Proceedings of Machine Learning Research"},{"key":"ref72","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume":"31","author":"lee","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.128"},{"key":"ref68","first-page":"3581","article-title":"A large-scale study on regularization and normalization in GANs","author":"kurach","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref119","article-title":"Noise or signal: The role of image backgrounds in object recognition","author":"xiao","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref67","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref117","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","author":"wang","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/5.58325"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref116","article-title":"Tent: Fully test-time adaptation by entropy minimization","author":"wang","year":"2021","journal-title":"International Conference on Learning Representations"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref66"},{"key":"ref113","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume":"33","author":"vahdat","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/e21121181"},{"key":"ref114","article-title":"Neural discrete representation learning","volume":"30","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref60","article-title":"Improved variational inference with inverse autoregressive flow","volume":"29","author":"kingma","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref122","article-title":"Full-spectrum out-of-distribution detection","author":"yang","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00643"},{"key":"ref62","first-page":"1012","article-title":"On the effectiveness of adversarial training against common corruptions","author":"kireev","year":"0","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref120","first-page":"20685","article-title":"Likelihood regret: An out-of-distribution detection score for variational autoencoder","volume":"33","author":"xiao","year":"2020","journal-title":"Advances in neural information processing systems"},{"journal-title":"Auto-encoding variational bayes","year":"2014","author":"kingma","key":"ref61"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00090"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2023,6,17]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10203661.pdf?arnumber=10203661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:55:39Z","timestamp":1694454939000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/10203661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":130,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/cvpr52729.2023.01555","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}