{"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/did-you-hear-that-adversarial-examples","title":"Did you hear that? Adversarial Examples Against Automatic Speech Recognition","arxiv_id":"1801.00554","date":"2018-01-02","proceeding":null,"authors":["Moustafa Alzantot","Bharathan Balaji","Mani Srivastava"],"abstract":"Speech is a common and effective way of communication between humans, and\nmodern consumer devices such as smartphones and home hubs are equipped with\ndeep learning based accurate automatic speech recognition to enable natural\ninteraction between humans and machines. Recently, researchers have\ndemonstrated powerful attacks against machine learning models that can fool\nthem to produceincorrect results. However, nearly all previous research in\nadversarial attacks has focused on image recognition and object detection\nmodels. In this short paper, we present a first of its kind demonstration of\nadversarial attacks against speech classification model. Our algorithm performs\ntargeted attacks with 87% success by adding small background noise without\nhaving to know the underlying model parameter and architecture. Our attack only\nchanges the least significant bits of a subset of audio clip samples, and the\nnoise does not change 89% the human listener's perception of the audio clip as\nevaluated in our human study.","url_abs":"http://arxiv.org/abs/1801.00554v1","url_pdf":"http://arxiv.org/pdf/1801.00554v1.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":"did-you-hear-that-adversarial-examples","repo_url":"https://github.com/nesl/adversarial_audio","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1801.00554","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}