{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:25:50Z","timestamp":1783787150230,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ontario Research Fund ? Research Excellence (ORF?RE)","award":["RE011-038"],"award-info":[{"award-number":["RE011-038"]}]},{"DOI":"10.13039\/501100006374","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2020-04744"],"award-info":[{"award-number":["RGPIN-2020-04744"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,19]]},"DOI":"10.1145\/3714393.3726502","type":"proceedings-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T18:38:47Z","timestamp":1749062327000},"page":"305-316","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["<scp>Espresso:<\/scp>\n                    Robust Concept Filtering in Text-to-Image Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9387-4437","authenticated-orcid":false,"given":"Anudeep","family":"Das","sequence":"first","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2138-4341","authenticated-orcid":false,"given":"Vasisht","family":"Duddu","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7885-5103","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5093-9871","authenticated-orcid":false,"given":"N.","family":"Asokan","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Nicholas Carlini et al. 2023a. (Certified!!) Adversarial Robustness for Free!. In ICLR. https:\/\/openreview.net\/forum?id=JLg5aHHv7j"},{"key":"e_1_3_2_1_2_1","unstructured":"Nicholas Carlini et al. 2023b. Extracting training data from diffusion models. In USENIX Security."},{"key":"e_1_3_2_1_3_1","unstructured":"Nicholas Carlini and Andreas Terzis. 2022. Poisoning and Backdooring Contrastive Learning. In ICLR. https:\/\/openreview.net\/forum?id=iC4UHbQ01Mp"},{"key":"e_1_3_2_1_4_1","unstructured":"Jeremy Cohen et al. 2019. Certified Adversarial Robustness via Randomized Smoothing. In ICML. 1310--1320. https:\/\/proceedings.mlr.press\/v97\/cohen19c.html"},{"key":"e_1_3_2_1_5_1","volume-title":"Espresso: Robust concept filtering in text-to-image models. In arXiv preprint arXiv:2404.19227.","author":"Anudeep Das","year":"2024","unstructured":"Anudeep Das et al. 2024. Espresso: Robust concept filtering in text-to-image models. In arXiv preprint arXiv:2404.19227."},{"key":"e_1_3_2_1_6_1","unstructured":"Will Friedwald. 2019. Captain Marvel vs. captain Marvel: The strange tale of two dueling superheroes. https:\/\/www.vanityfair.com\/hollywood\/2019\/03\/captain-marvel-shazam-carol-danvers-guide"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"e_1_3_2_1_8_1","unstructured":"Rinon Gal et al. 2023. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In ICLR. https:\/\/openreview.net\/forum?id=NAQvF08TcyG"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Rohit Gandikota et al. 2023a. Erasing Concepts from Diffusion Models. In ICCV. 2426--2436.","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Rohit Gandikota et al. 2023b. GitHub - Erasing Concepts from Diffusion Models. https:\/\/github.com\/rohitgandikota\/erasing.","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Rohit Gandikota et al. 2023c. GitHub - Unified Concept Editing in Diffusion Models. https:\/\/github.com\/rohitgandikota\/unified-concept-editing\/tree\/main.","DOI":"10.1109\/WACV57701.2024.00503"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Rohit Gandikota et al. 2024. Unified Concept Editing in Diffusion Models. In WACV. 5111--5120.","DOI":"10.1109\/WACV57701.2024.00503"},{"key":"e_1_3_2_1_13_1","unstructured":"Alvin Heng and Harold Soh. 2023a. GitHub - selective-amnesia. https:\/\/github.com\/clear-nus\/selective-amnesia\/tree\/main."},{"key":"e_1_3_2_1_14_1","volume-title":"Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models. In NeurIPS. https:\/\/openreview.net\/forum?id=BC1IJdsuYB","author":"Heng Alvin","year":"2023","unstructured":"Alvin Heng and Harold Soh. 2023b. Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models. In NeurIPS. https:\/\/openreview.net\/forum?id=BC1IJdsuYB"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Jack Hessel et al. 2021. CLIPScore: A Reference-free Evaluation Metric for Image Captioning. In EMNLP. 7514--7528. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.595","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_2_1_16_1","unstructured":"HuggingFace. 2021. openai\/clip-vit-large-patch14 \u00b7 Hugging Face. https:\/\/huggingface.co\/openai\/clip-vit-large-patch14"},{"key":"e_1_3_2_1_17_1","unstructured":"Gabriel Ilharco et al. 2023. Editing models with task arithmetic. In ICLR. https:\/\/openreview.net\/forum?id=6t0Kwf8-jrj"},{"key":"e_1_3_2_1_18_1","volume-title":"ICML Workshop on Challenges in Deployable Generative AI.","author":"Sanghyun","unstructured":"Sanghyun Kim et al. 2023. Towards safe self-distillation of internet-scale text-to-image diffusion models. In ICML Workshop on Challenges in Deployable Generative AI."},{"key":"e_1_3_2_1_19_1","unstructured":"Sanghyun Kim et al. 2024. GitHub - safe-diffusion. https:\/\/github.com\/nannullna\/safe-diffusion."},{"key":"e_1_3_2_1_20_1","unstructured":"Jennifer Korn. 2023. Getty Images suing the makers of popular AI art tool for allegedly stealing photos. In CNN Business. CNN. https:\/\/www.cnn.com\/2023\/01\/17\/tech\/getty-images-stability-ai-lawsuit\/index.html"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Nupur Kumari et al. 2023a. Ablating Concepts in Text-to-Image Diffusion Models. In ICCV.","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Nupur Kumari et al. 2023b. GitHub: Ablating Concepts in Text-to-Image Diffusion Models. https:\/\/github.com\/nupurkmr9\/concept-ablation.","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"e_1_3_2_1_23_1","unstructured":"Seung Hyun Lee et al. 2022. Sound-Guided Semantic Image Manipulation. In CVPR. 3377--3386."},{"key":"e_1_3_2_1_24_1","unstructured":"Xinfeng Li et al. 2024. SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models. In CCS."},{"key":"e_1_3_2_1_25_1","volume-title":"Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning. In NeurIPS. https:\/\/openreview.net\/forum?id=S7Evzt9uit3","author":"Weixin Liang","year":"2022","unstructured":"Weixin Liang et al. 2022. Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning. In NeurIPS. https:\/\/openreview.net\/forum?id=S7Evzt9uit3"},{"key":"e_1_3_2_1_26_1","unstructured":"Tsung-Yi Lin et al. 2014. Microsoft COCO: Common Objects in Context. In arXiv 1405.0312."},{"key":"e_1_3_2_1_27_1","unstructured":"Jiachen Ma et al. 2024. Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models. In arXiv:2404.02928."},{"key":"e_1_3_2_1_28_1","unstructured":"Meg Matthias. 2023. Why does AI art screw up hands and fingers? https:\/\/www.britannica.com\/topic\/Why-does-AI-art-screw-up-hands-and-fingers-2230501"},{"key":"e_1_3_2_1_29_1","volume-title":"Miller Noever","author":"Noever David A.","year":"2021","unstructured":"David A. Noever and Samantha E. Miller Noever. 2021. Reading Isn't Believing: Adversarial Attacks On Multi-Modal Neurons. In arXiv:2103.10480."},{"key":"e_1_3_2_1_30_1","unstructured":"Minh Pham et al. 2024a. Circumventing Concept Erasure Methods For Text-to-Image Generative Models. In ICLR."},{"key":"e_1_3_2_1_31_1","unstructured":"Minh Pham et al. 2024b. Robust Concept Erasure Using Task Vectors. In arXiv:2404.03631."},{"key":"e_1_3_2_1_32_1","unstructured":"Yiting Qu et al. 2023. GitHub: unsafe-diffusion. https:\/\/github.com\/YitingQu\/unsafe-diffusion\/tree\/main."},{"key":"e_1_3_2_1_33_1","unstructured":"Alec Radford et al. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML. 8748--8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_34_1","unstructured":"Aditya Ramesh et al. 2021. DALL\u00b7E 2: The Flower That Blooms in Adversity. In OpenAI Blog. OpenAI. https:\/\/openai.com\/blog\/dall-e-2\/"},{"key":"e_1_3_2_1_35_1","volume-title":"Red-Teaming the Stable Diffusion Safety Filter. In NeurIPS ML Safety Workshop.","author":"Javier","unstructured":"Javier Rando et al. [n.,d.]. Red-Teaming the Stable Diffusion Safety Filter. In NeurIPS ML Safety Workshop."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach et al. 2022a. High-Resolution Image Synthesis With Latent Diffusion Models. In CVPR. 10684--10695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach et al. 2022b. High-Resolution Image Synthesis With Latent Diffusion Models. In CVPR. 10684--10695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Patrick Schramowski et al. 2023. Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models. In CVPR.","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"e_1_3_2_1_39_1","unstructured":"Christoph Schuhmann et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. In NeurIPS. 1--2."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"G. Somepalli et al. 2023. Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models. In CVPR. 6048--6058.","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"e_1_3_2_1_41_1","unstructured":"Yu-Lin Tsai et al. 2024. Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?. In ICLR. https:\/\/openreview.net\/forum?id=lm7MRcsFiS"},{"key":"e_1_3_2_1_42_1","unstructured":"A\u00e4ron van den Oord et al. 2018. Representation Learning with Contrastive Predictive Coding. In arXiv:1807.03748."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1093\/owc\/9780198818649.001.0001"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Peiran Wang et al. 2024a. GitHub: Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies. https:\/\/github.com\/DataSmithLab\/Moderator.","DOI":"10.1145\/3658644.3690327"},{"key":"e_1_3_2_1_45_1","volume-title":"Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies. In CCS.","author":"Peiran Wang","year":"2024","unstructured":"Peiran Wang et al. 2024b. Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies. In CCS."},{"key":"e_1_3_2_1_46_1","unstructured":"Yuxin Wen et al. 2023. Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery. In NeurIPS. https:\/\/openreview.net\/forum?id=VOstHxDdsN"},{"key":"e_1_3_2_1_47_1","unstructured":"Wenhan Yang et al. 2023. Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks. In NeurIPS. https:\/\/openreview.net\/forum?id=ONwL9ucoYG"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Yuchen Yang et al. 2024. SneakyPrompt: Jailbreaking Text-to-image Generative Models. In SP.","DOI":"10.1109\/SP54263.2024.00123"},{"key":"e_1_3_2_1_49_1","volume-title":"Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models. In CCS.","author":"Qu Yiting","year":"2023","unstructured":"Qu Yiting et al. 2023. Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models. In CCS."},{"key":"e_1_3_2_1_50_1","unstructured":"Eric Zhang et al. 2023. GitHub - Forget-Me-Not. https:\/\/github.com\/SHI-Labs\/Forget-Me-Not."},{"key":"e_1_3_2_1_51_1","volume-title":"Forget-me-not: Learning to forget in text-to-image diffusion models. In CVPR. 1755--1764.","author":"Gong Zhang","year":"2024","unstructured":"Gong Zhang et al. 2024. Forget-me-not: Learning to forget in text-to-image diffusion models. In CVPR. 1755--1764."},{"key":"e_1_3_2_1_52_1","unstructured":"Hongyang Zhang et al. 2019. Theoretically principled trade-off between robustness and accuracy. In ICML. 7472--7482."}],"event":{"name":"CODASPY '25: Fifteenth ACM Conference on Data and Application Security and Privacy","location":"Pittsburgh PA USA","acronym":"CODASPY '25","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the Fifteenth ACM Conference on Data and Application Security and Privacy"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3714393.3726502","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3714393.3726502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:26:06Z","timestamp":1780417566000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3714393.3726502"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,19]]},"references-count":52,"alternative-id":["10.1145\/3714393.3726502","10.1145\/3714393"],"URL":"https:\/\/doi.org\/10.1145\/3714393.3726502","relation":{},"subject":[],"published":{"date-parts":[[2024,6,19]]},"assertion":[{"value":"2025-06-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}