{"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/are-you-tampering-with-my-data","title":"Are You Tampering With My Data?","arxiv_id":"1808.06809","date":"2018-08-21","proceeding":null,"authors":["Michele Alberti","Vinaychandran Pondenkandath","Marcel Würsch","Manuel Bouillon","Mathias Seuret","Rolf Ingold","Marcus Liwicki"],"abstract":"We propose a novel approach towards adversarial attacks on neural networks\n(NN), focusing on tampering the data used for training instead of generating\nattacks on trained models. Our network-agnostic method creates a backdoor\nduring training which can be exploited at test time to force a neural network\nto exhibit abnormal behaviour. We demonstrate on two widely used datasets\n(CIFAR-10 and SVHN) that a universal modification of just one pixel per image\nfor all the images of a class in the training set is enough to corrupt the\ntraining procedure of several state-of-the-art deep neural networks causing the\nnetworks to misclassify any images to which the modification is applied. Our\naim is to bring to the attention of the machine learning community, the\npossibility that even learning-based methods that are personally trained on\npublic datasets can be subject to attacks by a skillful adversary.","url_abs":"http://arxiv.org/abs/1808.06809v1","url_pdf":"http://arxiv.org/pdf/1808.06809v1.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":"are-you-tampering-with-my-data","repo_url":"https://github.com/vinaychandranp/Are-You-Tampering-With-My-Data","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}