{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T02:10:47Z","timestamp":1755828647894,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,7]],"date-time":"2023-12-07T00:00:00Z","timestamp":1701907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,7]]},"DOI":"10.1145\/3628797.3628949","type":"proceedings-article","created":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T15:25:34Z","timestamp":1701876334000},"page":"754-760","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Black-Box Adversarial Attacks Against Language Model Detector"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8527-4434","authenticated-orcid":false,"given":"Huyen","family":"Ha","sequence":"first","affiliation":[{"name":"Bach Khoa Cybersecurity Center, Hanoi University of Science and Technology, Viet Nam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7251-3516","authenticated-orcid":false,"given":"Duc","family":"Tran","sequence":"additional","affiliation":[{"name":"Bach Khoa Cybersecurity Center, Hanoi University of Science and Technology, Viet Nam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6918-968X","authenticated-orcid":false,"given":"Dukyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Bach Khoa Cybersecurity Center, Hanoi University of Science and Technology, Vietnam"}]}],"member":"320","published-online":{"date-parts":[[2023,12,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_1_2_1","volume-title":"Universal sentence encoder. arXiv preprint arXiv:1803.11175","author":"Cer Daniel","year":"2018","unstructured":"Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni\u00a0St John, Noah Constant, Mario Guajardo-Cespedes, Steve Yuan, Chris Tar, 2018. Universal sentence encoder. arXiv preprint arXiv:1803.11175 (2018)."},{"key":"e_1_3_2_1_3_1","volume-title":"Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung\u00a0Won Chung, Charles Sutton, Sebastian Gehrmann, 2022. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1109\/SPW.2018.00016"},{"key":"e_1_3_2_1_5_1","volume-title":"Bae: Bert-based adversarial examples for text classification. arXiv preprint arXiv:2004.01970","author":"Garg Siddhant","year":"2020","unstructured":"Siddhant Garg and Goutham Ramakrishnan. 2020. Bae: Bert-based adversarial examples for text classification. arXiv preprint arXiv:2004.01970 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Gltr: Statistical detection and visualization of generated text. arXiv preprint arXiv:1906.04043","author":"Gehrmann Sebastian","year":"2019","unstructured":"Sebastian Gehrmann, Hendrik Strobelt, and Alexander\u00a0M Rush. 2019. Gltr: Statistical detection and visualization of generated text. arXiv preprint arXiv:1906.04043 (2019)."},{"key":"e_1_3_2_1_7_1","volume-title":"How close is chatgpt to human experts? comparison corpus, evaluation, and detection. arXiv preprint arXiv:2301.07597","author":"Guo Biyang","year":"2023","unstructured":"Biyang Guo, Xin Zhang, Ziyuan Wang, Minqi Jiang, Jinran Nie, Yuxuan Ding, Jianwei Yue, and Yupeng Wu. 2023. How close is chatgpt to human experts? comparison corpus, evaluation, and detection. arXiv preprint arXiv:2301.07597 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Mgtbench: Benchmarking machine-generated text detection. arXiv preprint arXiv:2303.14822","author":"He Xinlei","year":"2023","unstructured":"Xinlei He, Xinyue Shen, Zeyuan Chen, Michael Backes, and Yang Zhang. 2023. Mgtbench: Benchmarking machine-generated text detection. arXiv preprint arXiv:2303.14822 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Human and Automatic Detection of Generated Text. CoRR abs\/1911.00650","author":"Ippolito Daphne","year":"2019","unstructured":"Daphne Ippolito, Daniel Duckworth, Chris Callison-Burch, and Douglas Eck. 2019. Human and Automatic Detection of Generated Text. CoRR abs\/1911.00650 (2019). arXiv:1911.00650http:\/\/arxiv.org\/abs\/1911.00650"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"e_1_3_2_1_11_1","volume-title":"Textbugger: Generating adversarial text against real-world applications. arXiv preprint arXiv:1812.05271","author":"Li Jinfeng","year":"2018","unstructured":"Jinfeng Li, Shouling Ji, Tianyu Du, Bo Li, and Ting Wang. 2018. Textbugger: Generating adversarial text against real-world applications. arXiv preprint arXiv:1812.05271 (2018)."},{"key":"e_1_3_2_1_12_1","volume-title":"Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958","author":"Lin Stephanie","year":"2021","unstructured":"Stephanie Lin, Jacob Hilton, and Owain Evans. 2021. Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958 (2021)."},{"key":"e_1_3_2_1_13_1","volume-title":"Detectgpt: Zero-shot machine-generated text detection using probability curvature. arXiv preprint arXiv:2301.11305","author":"Mitchell Eric","year":"2023","unstructured":"Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher\u00a0D Manning, and Chelsea Finn. 2023. Detectgpt: Zero-shot machine-generated text detection using probability curvature. arXiv preprint arXiv:2301.11305 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Reevaluating adversarial examples in natural language. arXiv preprint arXiv:2004.14174","author":"Morris X","year":"2020","unstructured":"John\u00a0X Morris, Eli Lifland, Jack Lanchantin, Yangfeng Ji, and Yanjun Qi. 2020. Reevaluating adversarial examples in natural language. arXiv preprint arXiv:2004.14174 (2020)."},{"key":"e_1_3_2_1_15_1","volume-title":"Textattack: A framework for adversarial attacks, data augmentation, and adversarial training in nlp. arXiv preprint arXiv:2005.05909","author":"Morris X","year":"2020","unstructured":"John\u00a0X Morris, Eli Lifland, Jin\u00a0Yong Yoo, Jake Grigsby, Di Jin, and Yanjun Qi. 2020. Textattack: A framework for adversarial attacks, data augmentation, and adversarial training in nlp. arXiv preprint arXiv:2005.05909 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"Counter-fitting word vectors to linguistic constraints. arXiv preprint arXiv:1603.00892","author":"Mrk\u0161i\u0107 Nikola","year":"2016","unstructured":"Nikola Mrk\u0161i\u0107, Diarmuid\u00a0O S\u00e9aghdha, Blaise Thomson, Milica Ga\u0161i\u0107, Lina Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young. 2016. Counter-fitting word vectors to linguistic constraints. arXiv preprint arXiv:1603.00892 (2016)."},{"key":"e_1_3_2_1_17_1","volume-title":"Combating adversarial misspellings with robust word recognition. arXiv preprint arXiv:1905.11268","author":"Pruthi Danish","year":"2019","unstructured":"Danish Pruthi, Bhuwan Dhingra, and Zachary\u00a0C Lipton. 2019. Combating adversarial misspellings with robust word recognition. arXiv preprint arXiv:1905.11268 (2019)."},{"key":"e_1_3_2_1_18_1","volume-title":"Language models are unsupervised multitask learners. OpenAI blog 1, 8","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9."},{"key":"e_1_3_2_1_19_1","volume-title":"100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250","author":"Rajpurkar Pranav","year":"2016","unstructured":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.18653\/v1\/P19-1103"},{"key":"e_1_3_2_1_21_1","volume-title":"Beyond accuracy: Behavioral testing of NLP models with CheckList. arXiv preprint arXiv:2005.04118","author":"Ribeiro Marco\u00a0Tulio","year":"2020","unstructured":"Marco\u00a0Tulio Ribeiro, Tongshuang Wu, Carlos Guestrin, and Sameer Singh. 2020. Beyond accuracy: Behavioral testing of NLP models with CheckList. arXiv preprint arXiv:2005.04118 (2020)."},{"unstructured":"Edward Tian and Alexander Cui. 2023. GPTZero: Towards detection of AI-generated text using zero-shot and supervised methods. https:\/\/gptzero.me","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","volume-title":"Searching for a search method: Benchmarking search algorithms for generating nlp adversarial examples. arXiv preprint arXiv:2009.06368","author":"Yoo Jin\u00a0Yong","year":"2020","unstructured":"Jin\u00a0Yong Yoo, John\u00a0X Morris, Eli Lifland, and Yanjun Qi. 2020. Searching for a search method: Benchmarking search algorithms for generating nlp adversarial examples. arXiv preprint arXiv:2009.06368 (2020)."},{"key":"e_1_3_2_1_24_1","volume-title":"Towards improving adversarial training of NLP models. arXiv preprint arXiv:2109.00544","author":"Yoo Jin\u00a0Yong","year":"2021","unstructured":"Jin\u00a0Yong Yoo and Yanjun Qi. 2021. Towards improving adversarial training of NLP models. arXiv preprint arXiv:2109.00544 (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Openattack: An open-source textual adversarial attack toolkit. arXiv preprint arXiv:2009.09191","author":"Zeng Guoyang","year":"2020","unstructured":"Guoyang Zeng, Fanchao Qi, Qianrui Zhou, Tingji Zhang, Zixian Ma, Bairu Hou, Yuan Zang, Zhiyuan Liu, and Maosong Sun. 2020. Openattack: An open-source textual adversarial attack toolkit. arXiv preprint arXiv:2009.09191 (2020)."},{"key":"e_1_3_2_1_26_1","volume-title":"Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi\u00a0Victoria Lin, 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."}],"event":{"acronym":"SOICT 2023","name":"SOICT 2023: The 12th International Symposium on Information and Communication Technology","location":"Ho Chi Minh Vietnam"},"container-title":["Proceedings of the 12th International Symposium on Information and Communication Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3628797.3628949","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3628797.3628949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T12:25:01Z","timestamp":1755779101000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3628797.3628949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,7]]},"references-count":26,"alternative-id":["10.1145\/3628797.3628949","10.1145\/3628797"],"URL":"https:\/\/doi.org\/10.1145\/3628797.3628949","relation":{},"subject":[],"published":{"date-parts":[[2023,12,7]]},"assertion":[{"value":"2023-12-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}