{"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/bppattack-stealthy-and-efficient-trojan","title":"BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning","arxiv_id":"2205.13383","date":"2022-05-26","proceeding":"CVPR 2022 1","authors":["Zhenting Wang","Juan Zhai","Shiqing Ma"],"abstract":"Deep neural networks are vulnerable to Trojan attacks. Existing attacks use visible patterns (e.g., a patch or image transformations) as triggers, which are vulnerable to human inspection. In this paper, we propose stealthy and efficient Trojan attacks, BppAttack. Based on existing biology literature on human visual systems, we propose to use image quantization and dithering as the Trojan trigger, making imperceptible changes. It is a stealthy and efficient attack without training auxiliary models. Due to the small changes made to images, it is hard to inject such triggers during training. To alleviate this problem, we propose a contrastive learning based approach that leverages adversarial attacks to generate negative sample pairs so that the learned trigger is precise and accurate. The proposed method achieves high attack success rates on four benchmark datasets, including MNIST, CIFAR-10, GTSRB, and CelebA. It also effectively bypasses existing Trojan defenses and human inspection. Our code can be found in https://github.com/RU-System-Software-and-Security/BppAttack.","url_abs":"https://arxiv.org/abs/2205.13383v1","url_pdf":"https://arxiv.org/pdf/2205.13383v1.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":"bppattack-stealthy-and-efficient-trojan","repo_url":"https://github.com/ru-system-software-and-security/bppattack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.13383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13383"}},"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/ru-system-software-and-security/bppattack","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/RU-System-Softwareand-Security/BppAttack","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":"8737c82de631cffc","entry":"swish","repo":"ru-system-software-and-security/bppattack","repo_kind":"official","path":"classifier_models/efficientnet.py","file_url":"https://github.com/ru-system-software-and-security/bppattack/blob/HEAD/classifier_models/efficientnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8737c82de631cffc"}},{"code_sha256_prefix":"009ef5196808279a","entry":"PreActResNet18","repo":"ru-system-software-and-security/bppattack","repo_kind":"official","path":"classifier_models/preact_resnet.py","file_url":"https://github.com/ru-system-software-and-security/bppattack/blob/HEAD/classifier_models/preact_resnet.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":"009ef5196808279a"}},{"code_sha256_prefix":"d7b18398e3610293","entry":"back_to_np","repo":"ru-system-software-and-security/bppattack","repo_kind":"official","path":"bppattack.py","file_url":"https://github.com/ru-system-software-and-security/bppattack/blob/HEAD/bppattack.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":"d7b18398e3610293"}},{"code_sha256_prefix":"47a3f7bec944c35b","entry":"back_to_np_4d","repo":"ru-system-software-and-security/bppattack","repo_kind":"official","path":"bppattack.py","file_url":"https://github.com/ru-system-software-and-security/bppattack/blob/HEAD/bppattack.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":"47a3f7bec944c35b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}