{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T22:27:29Z","timestamp":1766442449360,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"vor","delay-in-days":3,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2427316, 2426318"],"award-info":[{"award-number":["2427316, 2426318"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-24-1-0044"],"award-info":[{"award-number":["W911NF-24-1-0044"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,19]]},"DOI":"10.1145\/3719027.3765052","type":"proceedings-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T23:37:25Z","timestamp":1763854645000},"page":"4154-4168","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0782-4187","authenticated-orcid":false,"given":"Xiaoyong (Brian)","family":"Yuan","sequence":"first","affiliation":[{"name":"Clemson University, Clemson, South Carolina, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3753-7648","authenticated-orcid":false,"given":"Xiaolong","family":"Ma","sequence":"additional","affiliation":[{"name":"The University of Arizona, Tucson, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3658-7435","authenticated-orcid":false,"given":"Linke","family":"Guo","sequence":"additional","affiliation":[{"name":"Clemson University, Clemson, South Carolina, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7718-6128","authenticated-orcid":false,"given":"Lan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Clemson University, Clemson, South Carolina, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_4_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems, 27","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. Advances in neural information processing systems, 27, 2014."},{"key":"e_1_3_2_1_5_1","volume-title":"Auto-encoding variational bayes","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma, Max Welling, et al. Auto-encoding variational bayes, 2013."},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Learning Representations","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. Lora: Low-rank adaptation of large language models. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_1_7_1","volume-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach Robin","year":"2021","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. High-resolution image synthesis with latent diffusion models, 2021."},{"volume-title":"Accessed","year":"2025","key":"e_1_3_2_1_8_1","unstructured":"automatic1111. stable-diffusion-webui, 2025. https:\/\/github.com\/AUTOMATIC1111\/stable-diffusion-webui, Accessed: January 20, 2025."},{"volume-title":"Accessed","year":"2025","key":"e_1_3_2_1_9_1","unstructured":"Comfy. Comfyui, 2025. https:\/\/www.comfy.org\/, Accessed: January 20, 2025."},{"volume-title":"Accessed","year":"2025","key":"e_1_3_2_1_10_1","unstructured":"Civitai. Civitai models repository, 2025. https:\/\/civitai.com\/models, Accessed: January 20, 2025."},{"volume-title":"Accessed","year":"2025","key":"e_1_3_2_1_11_1","unstructured":"HuggingFace. Huggingface models for text-to-image generation, 2025. https:\/\/huggingface.co\/models?pipeline_tag=text-to-image, Accessed: January 20, 2025."},{"volume-title":"Accessed","year":"2025","key":"e_1_3_2_1_12_1","unstructured":"SeaArt. Seaart model repository, 2025. https:\/\/www.seaart.ai\/model, Accessed: January 20, 2025."},{"key":"e_1_3_2_1_13_1","volume-title":"Lim Wei Hern, Haonan Wang, and Kenji Kawaguchi. On copyright risks of text-to-image diffusion models. arXiv preprint arXiv:2311.12803","author":"Zhang Yang","year":"2023","unstructured":"Yang Zhang, Teoh Tze Tzun, Lim Wei Hern, Haonan Wang, and Kenji Kawaguchi. On copyright risks of text-to-image diffusion models. arXiv preprint arXiv:2311.12803, 2023."},{"key":"e_1_3_2_1_14_1","first-page":"2187","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Shan Shawn","year":"2023","unstructured":"Shawn Shan, Jenna Cryan, Emily Wenger, Haitao Zheng, Rana Hanocka, and Ben Y Zhao. Glaze: Protecting artists from style mimicry by {Text-to-Image} models. In 32nd USENIX Security Symposium (USENIX Security 23), pages 2187-2204, 2023."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02305"},{"key":"e_1_3_2_1_16_1","first-page":"3027","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Hao Qingying","year":"2024","unstructured":"Qingying Hao, Nirav Diwan, Ying Yuan, Giovanni Apruzzese, Mauro Conti, and Gang Wang. It doesn't look like anything to me: using diffusion model to subvert visual phishing detectors. In 33rd USENIX Security Symposium (USENIX Security 24), pages 3027-3044, 2024."},{"key":"e_1_3_2_1_17_1","volume-title":"European Conference on Computer Vision (ECCV)","author":"Zhang Yimeng","year":"2024","unstructured":"Yimeng Zhang, Jinghan Jia, Xin Chen, Aochuan Chen, Yihua Zhang, Jiancheng Liu, Ke Ding, and Sijia Liu. To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images... for now. European Conference on Computer Vision (ECCV), 2024."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00123"},{"key":"e_1_3_2_1_19_1","volume-title":"Prompting4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts. ArXiv, abs\/2309.06135","author":"Chin Zhi-Yi","year":"2023","unstructured":"Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen, and Wei-Chen Chiu. Prompting4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts. ArXiv, abs\/2309.06135, 2023."},{"key":"e_1_3_2_1_20_1","volume-title":"Red-teaming the stable diffusion safety filter. ArXiv, abs\/2210.04610","author":"Rando Javier","year":"2022","unstructured":"Javier Rando, Daniel Paleka, David Lindner, Lennard Heim, and Florian Tram\u00e8r. Red-teaming the stable diffusion safety filter. ArXiv, abs\/2210.04610, 2022."},{"key":"e_1_3_2_1_21_1","volume-title":"Neil Zhenqiang Gong, and Yinzhi Cao. Sneakyprompt: Evaluating robustness of text-to-image generative models' safety filters. ArXiv, abs\/2305.12082","author":"Yang Yuchen","year":"2023","unstructured":"Yuchen Yang, Bo Hui, Haolin Yuan, Neil Zhenqiang Gong, and Yinzhi Cao. Sneakyprompt: Evaluating robustness of text-to-image generative models' safety filters. ArXiv, abs\/2305.12082, 2023."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018046501280"},{"key":"e_1_3_2_1_23_1","volume-title":"A survey on concept drift adaptation. ACM computing surveys (CSUR), 46(4):1-37","author":"Gama Jo","year":"2014","unstructured":"Jo ao Gama, Indr.e \u017dliobait.e, Albert Bifet, Mykola Pechenizkiy, and Abdelhamid Bouchachia. A survey on concept drift adaptation. ACM computing surveys (CSUR), 46(4):1-37, 2014."},{"key":"e_1_3_2_1_24_1","first-page":"36","article-title":"Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery","author":"Wen Yuxin","year":"2024","unstructured":"Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, and Tom Goldstein. Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"Improving image generation with better captions. Computer Science. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf, 2(3):8","author":"Betker James","year":"2023","unstructured":"James Betker, Gabriel Goh, Li Jing, Tim Brooks, Jianfeng Wang, Linjie Li, Long Ouyang, Juntang Zhuang, Joyce Lee, Yufei Guo, et al. Improving image generation with better captions. Computer Science. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf, 2(3):8, 2023."},{"key":"e_1_3_2_1_26_1","volume-title":"Generated faces in the wild: Quantitative comparison of stable diffusion, midjourney and dall-e 2. arXiv preprint arXiv:2210.00586","author":"Borji Ali","year":"2022","unstructured":"Ali Borji. Generated faces in the wild: Quantitative comparison of stable diffusion, midjourney and dall-e 2. arXiv preprint arXiv:2210.00586, 2022."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26505"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_2_1_29_1","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume":"35","author":"Liu Haokun","year":"2022","unstructured":"Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin A Raffel. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Advances in Neural Information Processing Systems, 35:1950-1965, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton. Layer normalization. ArXiv e-prints","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. Layer normalization. ArXiv e-prints, pages arXiv-1607, 2016."},{"key":"e_1_3_2_1_31_1","volume-title":"Mike Zheng Shou, and J\u00fcrgen Schmidhuber. Cross-attention makes inference cumbersome in text-to-image diffusion models. arXiv preprint arXiv:2404.02747","author":"Zhang Wentian","year":"2024","unstructured":"Wentian Zhang, Haozhe Liu, Jinheng Xie, Francesco Faccio, Mike Zheng Shou, and J\u00fcrgen Schmidhuber. Cross-attention makes inference cumbersome in text-to-image diffusion models. arXiv preprint arXiv:2404.02747, 2024."},{"key":"e_1_3_2_1_32_1","volume-title":"Towards understanding the working mechanism of text-to-image diffusion model. arXiv preprint arXiv:2405.15330","author":"Yi Mingyang","year":"2024","unstructured":"Mingyang Yi, Aoxue Li, Yi Xin, and Zhenguo Li. Towards understanding the working mechanism of text-to-image diffusion model. arXiv preprint arXiv:2405.15330, 2024."},{"key":"e_1_3_2_1_33_1","first-page":"413","volume-title":"Kai Ming Ting, and Zhi-Hua Zhou. Isolation forest. In 2008 eighth ieee international conference on data mining","author":"Liu Fei Tony","year":"2008","unstructured":"Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou. Isolation forest. In 2008 eighth ieee international conference on data mining, pages 413-422. IEEE, 2008."},{"key":"e_1_3_2_1_34_1","first-page":"12888","volume-title":"International conference on machine learning","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning, pages 12888-12900. PMLR, 2022."},{"key":"e_1_3_2_1_35_1","volume-title":"Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100","author":"Wang Jianfeng","year":"2022","unstructured":"Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, and Lijuan Wang. Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100, 2022."},{"key":"e_1_3_2_1_36_1","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Hou Bairu","year":"2023","unstructured":"Bairu Hou, Jinghan Jia, Yihua Zhang, Guanhua Zhang, Yang Zhang, Sijia Liu, and Shiyu Chang. Textgrad: Advancing robustness evaluation in nlp by gradient-driven optimization. The Eleventh International Conference on Learning Representations (ICLR), 2023."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_38_1","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748-8763. PMLR, 2021."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401946"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1996.549118"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47578-3_1"},{"key":"e_1_3_2_1_42_1","volume-title":"One-class svms for document classification. Journal of machine Learning research, 2(Dec):139-154","author":"Manevitz Larry M","year":"2001","unstructured":"Larry M Manevitz and Malik Yousef. One-class svms for document classification. Journal of machine Learning research, 2(Dec):139-154, 2001."},{"key":"e_1_3_2_1_43_1","first-page":"22522","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Schramowski Patrick","year":"2022","unstructured":"Patrick Schramowski, Manuel Brack, Bjorn Deiseroth, and Kristian Kersting. Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 22522-22531, 2022."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"e_1_3_2_1_45_1","volume-title":"Towards safe self-distillation of internet-scale text-to-image diffusion models. ArXiv, abs\/2307.05977","author":"Kim Sanghyun","year":"2023","unstructured":"Sanghyun Kim, Seohyeong Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, and Juho Lee. Towards safe self-distillation of internet-scale text-to-image diffusion models. ArXiv, abs\/2307.05977, 2023."},{"key":"e_1_3_2_1_46_1","volume-title":"Safegen: Mitigating unsafe content generation in text-to-image models","author":"Li Xinfeng","year":"2024","unstructured":"Xinfeng Li, Yuchen Yang, Jiangyi Deng, Chen Yan, Yanjiao Chen, Xiaoyu Ji, and Wenyuan Xu. Safegen: Mitigating unsafe content generation in text-to-image models. 2024."},{"key":"e_1_3_2_1_47_1","volume-title":"To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images. .. for now. ArXiv, abs\/2310.11868","author":"Zhang Yimeng","year":"2023","unstructured":"Yimeng Zhang, Jinghan Jia, Xin Chen, Aochuan Chen, Yihua Zhang, Jiancheng Liu, Ke Ding, and Sijia Liu. To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images. .. for now. ArXiv, abs\/2310.11868, 2023."},{"key":"e_1_3_2_1_48_1","volume-title":"Mma-diffusion: Multimodal attack on diffusion models. ArXiv, abs\/2311.17516","author":"Yang Yijun","year":"2023","unstructured":"Yijun Yang, Ruiyuan Gao, Xiaosen Wang, Nan Xu, and Qiang Xu. Mma-diffusion: Multimodal attack on diffusion models. ArXiv, abs\/2311.17516, 2023."},{"key":"e_1_3_2_1_49_1","volume-title":"Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery. ArXiv, abs\/2302.03668","author":"Wen Yuxin","year":"2023","unstructured":"Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, and Tom Goldstein. Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery. ArXiv, abs\/2302.03668, 2023."},{"key":"e_1_3_2_1_50_1","first-page":"5253","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Carlini Nicolas","year":"2023","unstructured":"Nicolas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramer, Borja Balle, Daphne Ippolito, and Eric Wallace. Extracting training data from diffusion models. In 32nd USENIX Security Symposium (USENIX Security 23), pages 5253-5270, 2023."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"e_1_3_2_1_52_1","first-page":"8717","volume-title":"International Conference on Machine Learning","author":"Duan Jinhao","year":"2023","unstructured":"Jinhao Duan, Fei Kong, Shiqi Wang, Xiaoshuang Shi, and Kaidi Xu. Are diffusion models vulnerable to membership inference attacks? In International Conference on Machine Learning, pages 8717-8730. PMLR, 2023."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPW59333.2023.00013"},{"key":"e_1_3_2_1_54_1","volume-title":"Could it be generated? towards practical analysis of memorization in text-to-image diffusion models. arXiv preprint arXiv:2405.05846","author":"Ma Zhe","year":"2024","unstructured":"Zhe Ma, Xuhong Zhang, Qingming Li, Tianyu Du, Wenzhi Chen, Zonghui Wang, and Shouling Ji. Could it be generated? towards practical analysis of memorization in text-to-image diffusion models. arXiv preprint arXiv:2405.05846, 2024."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_1_56_1","volume-title":"An improved method for personalizing diffusion models. arXiv preprint arXiv:2407.05312","author":"Zeng Yan","year":"2024","unstructured":"Yan Zeng, Masanori Suganuma, and Takayuki Okatani. An improved method for personalizing diffusion models. arXiv preprint arXiv:2407.05312, 2024."},{"key":"e_1_3_2_1_57_1","volume-title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora. arXiv preprint arXiv:2304.06027","author":"Smith James Seale","year":"2023","unstructured":"James Seale Smith, Yen-Chang Hsu, Lingyu Zhang, Ting Hua, Zsolt Kira, Yilin Shen, and Hongxia Jin. Continual diffusion: Continual customization of text-to-image diffusion with c-lora. arXiv preprint arXiv:2304.06027, 2023."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00615"},{"key":"e_1_3_2_1_59_1","first-page":"457","volume-title":"European Conference on Computer Vision","author":"Liu Zhili","year":"2024","unstructured":"Zhili Liu, Kai Chen, Yifan Zhang, Jianhua Han, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-Yan Yeung, and James T Kwok. Implicit concept removal of diffusion models. In European Conference on Computer Vision, pages 457-473. Springer, 2024."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00123"},{"key":"e_1_3_2_1_62_1","volume-title":"Shielddiff: Suppressing sexual content generation from diffusion models through reinforcement learning. arXiv preprint arXiv:2410.05309","author":"Han Dong","year":"2024","unstructured":"Dong Han, Salaheldin Mohamed, and Yong Li. Shielddiff: Suppressing sexual content generation from diffusion models through reinforcement learning. arXiv preprint arXiv:2410.05309, 2024."},{"key":"e_1_3_2_1_63_1","volume-title":"Safe and reliable diffusion models via subspace projection. arXiv preprint arXiv:2503.16835","author":"Chen Huiqiang","year":"2025","unstructured":"Huiqiang Chen, Tianqing Zhu, Linlin Wang, Xin Yu, Longxiang Gao, and Wanlei Zhou. Safe and reliable diffusion models via subspace projection. arXiv preprint arXiv:2503.16835, 2025."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01237"},{"key":"e_1_3_2_1_65_1","volume-title":"Comprehensive evaluation and analysis for nsfw concept erasure in text-to-image diffusion models. arXiv preprint arXiv:2505.15450","author":"Chen Die","year":"2025","unstructured":"Die Chen, Zhiwen Li, Cen Chen, Yuexiang Xie, Xiaodan Li, Jinyan Ye, Yingda Chen, and Yaliang Li. Comprehensive evaluation and analysis for nsfw concept erasure in text-to-image diffusion models. arXiv preprint arXiv:2505.15450, 2025."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00393"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612108"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00391"},{"key":"e_1_3_2_1_69_1","first-page":"36","article-title":"A unified backdoor attack framework for diffusion models","author":"Chou Sheng-Yen","year":"2024","unstructured":"Sheng-Yen Chou, Pin-Yu Chen, and Tsung-Yi Ho. Villandiffusion: A unified backdoor attack framework for diffusion models. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28958"},{"key":"e_1_3_2_1_71_1","volume-title":"Terd: A unified framework for safeguarding diffusion models against backdoors. arXiv preprint arXiv:2409.05294","author":"Mo Yichuan","year":"2024","unstructured":"Yichuan Mo, Hui Huang, Mingjie Li, Ang Li, and Yisen Wang. Terd: A unified framework for safeguarding diffusion models against backdoors. arXiv preprint arXiv:2409.05294, 2024."},{"key":"e_1_3_2_1_72_1","volume-title":"Disdet: Exploring detectability of backdoor attack on diffusion models. arXiv preprint arXiv:2402.02739","author":"Sui Yang","year":"2024","unstructured":"Yang Sui, Huy Phan, Jinqi Xiao, Tianfang Zhang, Zijie Tang, Cong Shi, Yan Wang, Yingying Chen, and Bo Yuan. Disdet: Exploring detectability of backdoor attack on diffusion models. arXiv preprint arXiv:2402.02739, 2024."}],"event":{"name":"CCS '25: ACM SIGSAC Conference on Computer and Communications Security","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"],"location":"Taipei Taiwan","acronym":"CCS '25"},"container-title":["Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3719027.3765052","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3719027.3765052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T22:25:10Z","timestamp":1766442310000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3719027.3765052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":72,"alternative-id":["10.1145\/3719027.3765052","10.1145\/3719027"],"URL":"https:\/\/doi.org\/10.1145\/3719027.3765052","relation":{},"subject":[],"published":{"date-parts":[[2025,11,19]]},"assertion":[{"value":"2025-11-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}