{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:18:03Z","timestamp":1775081883533,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Innovation for Defence Excellence and Security (IDEaS) Program from the Department of National Defence","award":["MN3-005"],"award-info":[{"award-number":["MN3-005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tifs.2026.3675424","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:37:50Z","timestamp":1773862670000},"page":"3297-3311","source":"Crossref","is-referenced-by-count":0,"title":["A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3072-7905","authenticated-orcid":false,"given":"Vu Tuan","family":"Truong","sequence":"first","affiliation":[{"name":"INRS, University of Québec, Montréal, QC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3577-6530","authenticated-orcid":false,"given":"Long Bao","family":"Le","sequence":"additional","affiliation":[{"name":"INRS, University of Québec, Montréal, QC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref2","article-title":"Learning fast samplers for diffusion models by differentiating through sample quality","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Watson"},{"key":"ref3","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref4","first-page":"12533","article-title":"D2C: Diffusion-decoding models for few-shot conditional generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Sinha"},{"key":"ref5","article-title":"Analytic-DPM: An analytic estimate of the optimal reverse variance in diffusion probabilistic models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bao"},{"key":"ref6","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Austin"},{"key":"ref7","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume-title":"Proc. NIPS","author":"Hoogeboom"},{"key":"ref8","first-page":"4328","article-title":"Diffusion-lm improves controllable text generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Li"},{"key":"ref9","article-title":"Step-unrolled denoising autoencoders for text generation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Savinov"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC57260.2024.10571062"},{"key":"ref12","article-title":"DreamFusion: Text-to-3D using 2D diffusion","author":"Poole","year":"2022","journal-title":"arXiv:2209.14988"},{"key":"ref13","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref14","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov"},{"key":"ref15","first-page":"24804","article-title":"CSDI: Conditional score-based diffusion models for probabilistic time series imputation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Tashiro"},{"key":"ref16","article-title":"ScoreGrad: Multivariate probabilistic time series forecasting with continuous energy-based generative models","author":"Yan","year":"2021","journal-title":"arXiv:2106.10121"},{"key":"ref17","article-title":"Multivariate probabilistic time series forecasting via conditioned normalizing flows","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rasul"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref19","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kingma"},{"key":"ref20","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"37","author":"Rezende"},{"key":"ref21","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref22","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref23","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3721479"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3182979"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00031"},{"key":"ref28","article-title":"Detecting backdoor attacks on deep neural networks by activation clustering","author":"Chen","year":"2018","journal-title":"arXiv:1811.03728"},{"key":"ref29","article-title":"DISTIL: Data-free inversion of suspicious trojan inputs via latent diffusion","author":"Mirzaei","year":"2025","journal-title":"arXiv:2507.22813"},{"key":"ref30","article-title":"Distilling cognitive backdoor patterns within an image","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Huang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01569"},{"key":"ref32","article-title":"Detecting backdoor samples in contrastive language image pretraining","author":"Huang","year":"2025","journal-title":"arXiv:2502.01385"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3579856.3582822"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28958"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i26.34941"},{"key":"ref36","article-title":"DisDet: Exploring detectability of backdoor attack on diffusion models","author":"Sui","year":"2024","journal-title":"arXiv:2402.02739"},{"key":"ref37","article-title":"Diff-cleanse: Identifying and mitigating backdoor attacks in diffusion models","author":"Hao","year":"2024","journal-title":"arXiv:2407.21316"},{"key":"ref38","article-title":"TERD: A unified framework for safeguarding diffusion models against backdoors","author":"Mo","year":"2024","journal-title":"arXiv:2409.05294"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00391"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00393"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1471"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01787"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00423"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612108"},{"key":"ref47","first-page":"82265","article-title":"From trojan horses to castle walls: Unveiling bilateral backdoor effects in diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref48","article-title":"The stronger the diffusion model, the easier the backdoor: Data poisoning to induce copyright breaches without adjusting finetuning pipeline","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref49","article-title":"Learnable invisible backdoor for diffusion models","author":"Li","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_7"},{"key":"ref51","article-title":"CopyrightShield: Enhancing diffusion model security against copyright infringement attacks","author":"Guo","year":"2024","journal-title":"arXiv:2412.01528"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICC52391.2025.11161175"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref54","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3581026"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/11313711\/11442803.pdf?arnumber=11442803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:11:41Z","timestamp":1775074301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11442803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tifs.2026.3675424","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}