{"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/targeted-adversarial-examples-for-black-box","title":"Targeted Adversarial Examples for Black Box Audio Systems","arxiv_id":"1805.07820","date":"2018-05-20","proceeding":null,"authors":["Rohan Taori","Amog Kamsetty","Brenton Chu","Nikita Vemuri"],"abstract":"The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into incorrectly predicting a specified target with high confidence. Current work on fooling ASR systems have focused on white-box attacks, in which the model architecture and parameters are known. In this paper, we adopt a black-box approach to adversarial generation, combining the approaches of both genetic algorithms and gradient estimation to solve the task. We achieve a 89.25% targeted attack similarity after 3000 generations while maintaining 94.6% audio file similarity.","url_abs":"https://arxiv.org/abs/1805.07820v2","url_pdf":"https://arxiv.org/pdf/1805.07820v2.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":"targeted-adversarial-examples-for-black-box","repo_url":"https://github.com/rtaori/Black-Box-Audio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"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":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.07820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07820"}},"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/rtaori/Black-Box-Audio","reach":{"status":"ok","spdx":"MIT"}}],"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":"ee1169ece28e0d9d","entry":"levenshteinDistance","repo":"rtaori/Black-Box-Audio","repo_kind":"official","path":"run_audio_attack.py","file_url":"https://github.com/rtaori/Black-Box-Audio/blob/HEAD/run_audio_attack.py","link_basis":"plan_row","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":"ee1169ece28e0d9d"}},{"code_sha256_prefix":"87ac570e0397378d","entry":"compute_mfcc","repo":"rtaori/Black-Box-Audio","repo_kind":"official","path":"tf_logits.py","file_url":"https://github.com/rtaori/Black-Box-Audio/blob/HEAD/tf_logits.py","link_basis":"first_harvest_node","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":"87ac570e0397378d"}},{"code_sha256_prefix":"bb96e601ec97efe2","entry":"db","repo":"rtaori/Black-Box-Audio","repo_kind":"official","path":"run_audio_attack.py","file_url":"https://github.com/rtaori/Black-Box-Audio/blob/HEAD/run_audio_attack.py","link_basis":"first_harvest_node","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":"bb96e601ec97efe2"}},{"code_sha256_prefix":"d97455fb04cfa0d6","entry":"load_wav","repo":"rtaori/Black-Box-Audio","repo_kind":"official","path":"run_audio_attack.py","file_url":"https://github.com/rtaori/Black-Box-Audio/blob/HEAD/run_audio_attack.py","link_basis":"first_harvest_node","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":"d97455fb04cfa0d6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}