{"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/adversarial-attacks-on-deep-neural-networks","title":"Adversarial Attacks on Deep Neural Networks for Time Series Classification","arxiv_id":"1903.07054","date":"2019-03-17","proceeding":null,"authors":["Hassan Ismail Fawaz","Germain Forestier","Jonathan Weber","Lhassane Idoumghar","Pierre-Alain Muller"],"abstract":"Time Series Classification (TSC) problems are encountered in many real life\ndata mining tasks ranging from medicine and security to human activity\nrecognition and food safety. With the recent success of deep neural networks in\nvarious domains such as computer vision and natural language processing,\nresearchers started adopting these techniques for solving time series data\nmining problems. However, to the best of our knowledge, no previous work has\nconsidered the vulnerability of deep learning models to adversarial time series\nexamples, which could potentially make them unreliable in situations where the\ndecision taken by the classifier is crucial such as in medicine and security.\nFor computer vision problems, such attacks have been shown to be very easy to\nperform by altering the image and adding an imperceptible amount of noise to\ntrick the network into wrongly classifying the input image. Following this line\nof work, we propose to leverage existing adversarial attack mechanisms to add a\nspecial noise to the input time series in order to decrease the network's\nconfidence when classifying instances at test time. Our results reveal that\ncurrent state-of-the-art deep learning time series classifiers are vulnerable\nto adversarial attacks which can have major consequences in multiple domains\nsuch as food safety and quality assurance.","url_abs":"http://arxiv.org/abs/1903.07054v2","url_pdf":"http://arxiv.org/pdf/1903.07054v2.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":"adversarial-attacks-on-deep-neural-networks","repo_url":"https://github.com/hfawaz/ijcnn19attacks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"human-activity-recognition","task_name":"Human Activity Recognition"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-classification","task_name":"Time Series Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.07054","atlas_url":"https://app.syntology.ai/?focus=1903.07054","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}