{"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/unified-adversarial-patch-for-cross-modal","title":"Unified Adversarial Patch for Cross-modal Attacks in the Physical World","arxiv_id":"2307.07859","date":"2023-07-15","proceeding":"ICCV 2023 1","authors":["Xingxing Wei","Yao Huang","Yitong Sun","Jie Yu"],"abstract":"Recently, physical adversarial attacks have been presented to evade DNNs-based object detectors. To ensure the security, many scenarios are simultaneously deployed with visible sensors and infrared sensors, leading to the failures of these single-modal physical attacks. To show the potential risks under such scenes, we propose a unified adversarial patch to perform cross-modal physical attacks, i.e., fooling visible and infrared object detectors at the same time via a single patch. Considering different imaging mechanisms of visible and infrared sensors, our work focuses on modeling the shapes of adversarial patches, which can be captured in different modalities when they change. To this end, we design a novel boundary-limited shape optimization to achieve the compact and smooth shapes, and thus they can be easily implemented in the physical world. In addition, to balance the fooling degree between visible detector and infrared detector during the optimization process, we propose a score-aware iterative evaluation, which can guide the adversarial patch to iteratively reduce the predicted scores of the multi-modal sensors. We finally test our method against the one-stage detector: YOLOv3 and the two-stage detector: Faster RCNN. Results show that our unified patch achieves an Attack Success Rate (ASR) of 73.33% and 69.17%, respectively. More importantly, we verify the effective attacks in the physical world when visible and infrared sensors shoot the objects under various settings like different angles, distances, postures, and scenes.","url_abs":"https://arxiv.org/abs/2307.07859v2","url_pdf":"https://arxiv.org/pdf/2307.07859v2.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":"unified-adversarial-patch-for-cross-modal","repo_url":"https://github.com/aries-iai/cross-modal_patch_attack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"logistic-regression","method_name":"Logistic Regression"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"yolov3","method_name":"YOLOv3"},{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.07859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07859"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aries-iai/cross-modal_patch_attack","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":9},"by_repo_kind":{"listed":{"samples":10,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"988a3c854b1b13d0","entry":"autopad","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"yolov3/models/common.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/yolov3/models/common.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"988a3c854b1b13d0"}},{"code_sha256_prefix":"6e2c4123ff49ea80","entry":"compute_dis","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"attack_utils/spline.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/attack_utils/spline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e2c4123ff49ea80"}},{"code_sha256_prefix":"30a8ee34752d3fb4","entry":"cross","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"attack_utils/spline.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/attack_utils/spline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30a8ee34752d3fb4"}},{"code_sha256_prefix":"e29634d93c5178f8","entry":"custom","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"yolov3/hubconf.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/yolov3/hubconf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e29634d93c5178f8"}},{"code_sha256_prefix":"aab637864c086647","entry":"get_state","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"spline_DE_attack.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/spline_DE_attack.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aab637864c086647"}},{"code_sha256_prefix":"89d475d77e7aa9a2","entry":"ifcross","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"attack_utils/spline.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/attack_utils/spline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89d475d77e7aa9a2"}},{"code_sha256_prefix":"9f92d6e6f7a4cf15","entry":"img_process","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"attack_utils/multi_angles_transform_inf.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/attack_utils/multi_angles_transform_inf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f92d6e6f7a4cf15"}},{"code_sha256_prefix":"ca197255ebcd19f7","entry":"limit_region","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"spline_DE_attack.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/spline_DE_attack.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca197255ebcd19f7"}},{"code_sha256_prefix":"933e3e3518a0fbcc","entry":"yolov3","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"yolov3/hubconf.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/yolov3/hubconf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"933e3e3518a0fbcc"}},{"code_sha256_prefix":"bc00ccb584e433ec","entry":"yolov3_spp","repo":"aries-iai/cross-modal_patch_attack","repo_kind":"listed","path":"yolov3/hubconf.py","file_url":"https://github.com/aries-iai/cross-modal_patch_attack/blob/HEAD/yolov3/hubconf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc00ccb584e433ec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}