{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T10:43:01Z","timestamp":1768992181924,"version":"3.49.0"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650024","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Adversarial Examples are Misaligned in Diffusion Model Manifolds"],"prefix":"10.1109","author":[{"given":"Peter","family":"Lorenz","sequence":"first","affiliation":[{"name":"ITWM Fraunhofer Heidelberg University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ricard","family":"Durall","sequence":"additional","affiliation":[{"name":"ITWM Fraunhofer"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janis","family":"Keuper","sequence":"additional","affiliation":[{"name":"Offenburg University University of Mannheim,IMLA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"ref2","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref3","article-title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","volume-title":"ICML","author":"Athalye"},{"key":"ref4","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref5","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"ICML","author":"Zhang"},{"key":"ref6","article-title":"Robustart: Benchmarking robustness on architecture design and training techniques","author":"Tang","year":"2021"},{"key":"ref7","article-title":"Pixeldefend: Leveraging generative models to understand and defend against adversarial examples","author":"Song","year":"2017"},{"key":"ref8","article-title":"Protecting classifiers against adversarial attacks using generative models. arxiv 2018","volume":"1","author":"Samangouei","year":"2018"},{"key":"ref9","article-title":"Certified defenses against adversarial examples","author":"Raghunathan","year":"2018"},{"key":"ref10","first-page":"5286","article-title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","volume-title":"ICML","author":"Wong"},{"key":"ref11","article-title":"Certified adversarial robustness via randomized smoothing","volume-title":"ICML","author":"Cohen"},{"key":"ref12","article-title":"Beyond imagenet attack: Towards crafting adversarial examples for black-box domains","author":"Zhang","year":"2022"},{"key":"ref13","article-title":"Diffusion models for imperceptible and transferable adversarial attack","author":"Chen","year":"2023"},{"key":"ref14","article-title":"Synthesizing robust adversarial examples","volume-title":"ICML","author":"Athalye"},{"key":"ref15","article-title":"On adaptive attacks to adversarial example defenses","author":"Tramer","year":"2020","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00040"},{"key":"ref17","article-title":"Evaluating the adversarial robustness of adaptive test-time defenses","volume-title":"ICML","author":"Croce"},{"key":"ref18","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref19","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref20","article-title":"Densepure: Understanding diffusion models towards adversarial robustness","author":"Xiao","year":"2022"},{"key":"ref21","article-title":"{DiffSmooth} : Certifiably robust learning via diffusion models and local smoothing","volume-title":"USENIX Security Symposium","author":"Zhang"},{"key":"ref22","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref23","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Towards the detection of diffusion model deepfakes","author":"Ricker","year":"2022"},{"key":"ref25","article-title":"Diffusion models for adversarial purification","author":"Nie","year":"2022"},{"key":"ref26","article-title":"Robust classification via a single diffusion model","author":"Chen","year":"2023"},{"key":"ref27","article-title":"Defending against adversarial attacks by leveraging an entire gan","author":"Santhanam","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00461"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref31","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"ICML","author":"Croce"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref33","article-title":"Black-box adversarial attacks with limited queries and information","volume-title":"ICML","author":"Ilyas"},{"key":"ref34","article-title":"Prior convictions: Black-box adversarial attacks with bandits and priors","author":"Ilyas","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_29"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533442"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5220\/0011586500003417"},{"key":"ref38","article-title":"Characterizing adversarial subspaces using local intrinsic dimensionality","author":"Ma","year":"2018"},{"key":"ref39","article-title":"On the limitation of local intrinsic dimensionality for characterizing the subspaces of adversarial examples","author":"Lu","year":"2018"},{"key":"ref40","article-title":"Class-disentanglement and applications in adversarial detection and defense","author":"Yang","year":"2021","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140444"},{"key":"ref42","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","author":"Lee","year":"2018","journal-title":"NeurIPS"},{"key":"ref43","article-title":"Fixing data augmentation to improve adversarial robustness","author":"Rebuffi","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00125-2"},{"key":"ref45","article-title":"Adversarial training and robustness for multiple perturbations","author":"Tramer","year":"2019","journal-title":"NeurIPS"},{"key":"ref46","article-title":"Perceptual adversarial robustness: Defense against unseen threat models","author":"Laidlaw","year":"2020"},{"key":"ref47","article-title":"A survey on transferability of adversarial examples across deep neural networks","author":"Gu","year":"2023"},{"key":"ref48","article-title":"Evading defenses to transferable adversarial examples by mitigating attention shift","author":"Dong","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00444"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00196"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119491"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPS-ISA56441.2022.00041"},{"key":"ref53","article-title":"Diffusion models: A comprehensive survey of methods and applications","author":"Yang","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"ref54","article-title":"Better diffusion models further improve adversarial training","author":"Wang","year":"2023"},{"key":"ref55","article-title":"Improved denoising diffusion probabilistic models","volume-title":"ICML","author":"Nichol"},{"key":"ref56","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","article-title":"Towards lightweight black-box attack against deep neural networks","author":"Sun","year":"2022","journal-title":"NeurIPS"},{"key":"ref59","article-title":"Improved-diffusion","year":"2021"},{"key":"ref60","volume-title":"Guided-diffusion","year":"2021"},{"key":"ref61","article-title":"512x512 diffusion unconditional imagenet","year":"2021"},{"key":"ref62","article-title":"Pytorch playground","author":"Xichen","year":"2017"},{"key":"ref63","article-title":"Pretrained resn18 on cifar10","year":"2021"},{"key":"ref64","article-title":"Robust principles: Architectural design principles for adversarially robust cnns","author":"Peng","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097245"},{"key":"ref66","article-title":"Attacking adversarial attacks as a defense","author":"Wu","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126251"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00070"},{"key":"ref69","article-title":"Detecting autoattack perturbations in the frequency domain","author":"Lorenz","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02196-3"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00019"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650024.pdf?arnumber=10650024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:55:32Z","timestamp":1725944132000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650024\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650024","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}