{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mmcert-provable-defense-against-adversarial","title":"MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models","arxiv_id":"2403.19080","date":"2024-03-28","proceeding":"CVPR 2024 1","authors":["Yanting Wang","Hongye Fu","Wei Zou","Jinyuan Jia"],"abstract":"Different from a unimodal model whose input is from a single modality, the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image, 3D points, audio, text, etc. Similar to unimodal models, many existing studies show that a multi-modal model is also vulnerable to adversarial perturbation, where an attacker could add small perturbation to all modalities of a multi-modal input such that the multi-modal model makes incorrect predictions for it. Existing certified defenses are mostly designed for unimodal models, which achieve sub-optimal certified robustness guarantees when extended to multi-modal models as shown in our experimental results. In our work, we propose MMCert, the first certified defense against adversarial attacks to a multi-modal model. We derive a lower bound on the performance of our MMCert under arbitrary adversarial attacks with bounded perturbations to both modalities (e.g., in the context of auto-driving, we bound the number of changed pixels in both RGB image and depth image). We evaluate our MMCert using two benchmark datasets: one for the multi-modal road segmentation task and the other for the multi-modal emotion recognition task. Moreover, we compare our MMCert with a state-of-the-art certified defense extended from unimodal models. Our experimental results show that our MMCert outperforms the baseline.","url_abs":"https://arxiv.org/abs/2403.19080v3","url_pdf":"https://arxiv.org/pdf/2403.19080v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mmcert-provable-defense-against-adversarial","repo_url":"https://github.com/WYT8506/MultimodalCertification","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"road-segementation","task_name":"Road Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.19080","atlas_url":"https://app.syntology.ai/?focus=2403.19080","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}