{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:50:13Z","timestamp":1784303413586,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"US Army International Technology Center Indo-Pacific","award":["FA520921P0015"],"award-info":[{"award-number":["FA520921P0015"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,12,5]]},"DOI":"10.1145\/3564625.3567985","type":"proceedings-article","created":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T01:01:29Z","timestamp":1670029289000},"page":"481-496","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":113,"title":["Transformer-Based Language Models for Software Vulnerability Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3855-3378","authenticated-orcid":false,"given":"Chandra","family":"Thapa","sequence":"first","affiliation":[{"name":"CSIRO's Data61, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0544-7982","authenticated-orcid":false,"given":"Seung Ick","family":"Jang","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8033-0998","authenticated-orcid":false,"given":"Muhammad Ejaz","family":"Ahmed","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6353-8359","authenticated-orcid":false,"given":"Seyit","family":"Camtepe","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1917-6466","authenticated-orcid":false,"given":"Josef","family":"Pieprzyk","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, Australia and Institute of Computer Science, Polish Academy of Sciences, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3289-6599","authenticated-orcid":false,"given":"Surya","family":"Nepal","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,12,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Wasi\u00a0Uddin Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2021. Unified Pre-training for Program Understanding and Generation. CoRR abs\/2103.06333(2021). arXiv:2103.06333https:\/\/arxiv.org\/abs\/2103.06333  Wasi\u00a0Uddin Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2021. Unified Pre-training for Program Understanding and Generation. CoRR abs\/2103.06333(2021). arXiv:2103.06333https:\/\/arxiv.org\/abs\/2103.06333"},{"key":"e_1_3_2_1_2_1","unstructured":"Anaconda. [n. d.]. Anaconda. https:\/\/www.anaconda.com  Anaconda. [n. d.]. Anaconda. https:\/\/www.anaconda.com"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"e_1_3_2_1_4_1","unstructured":"Coverity. 2022. Coverity. https:\/\/scan.coverity.com\/  Coverity. 2022. Coverity. https:\/\/scan.coverity.com\/"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/648"},{"key":"e_1_3_2_1_7_1","volume-title":"Transformers: State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow. https:\/\/huggingface.co\/docs\/transformers\/index","author":"Face Hugging","year":"2022","unstructured":"Hugging Face . 2022 . Transformers: State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow. https:\/\/huggingface.co\/docs\/transformers\/index Hugging Face. 2022. Transformers: State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow. https:\/\/huggingface.co\/docs\/transformers\/index"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_9_1","unstructured":"The\u00a0Linux Foundation. 2022. Horovod. https:\/\/horovod.ai  The\u00a0Linux Foundation. 2022. Horovod. https:\/\/horovod.ai"},{"key":"e_1_3_2_1_10_1","volume-title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv preprint arXiv:2101.00027(2020).","author":"Gao Leo","year":"2020","unstructured":"Leo Gao , Stella Biderman , Sid Black , Laurence Golding , Travis Hoppe , Charles Foster , Jason Phang , Horace He , Anish Thite , Noa Nabeshima , Shawn Presser , and Connor Leahy . 2020 . The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv preprint arXiv:2101.00027(2020). Leo Gao, Stella Biderman, Sid Black, Laurence Golding, Travis Hoppe, Charles Foster, Jason Phang, Horace He, Anish Thite, Noa Nabeshima, Shawn Presser, and Connor Leahy. 2020. The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv preprint arXiv:2101.00027(2020)."},{"key":"e_1_3_2_1_11_1","unstructured":"Google. 2020. Atheris. https:\/\/pypi.org\/project\/atheris\/.  Google. 2020. Atheris. https:\/\/pypi.org\/project\/atheris\/."},{"key":"e_1_3_2_1_12_1","unstructured":"Daya Guo Shuo Ren Shuai Lu Zhangyin Feng Duyu Tang Shujie Liu Long Zhou Nan Duan Alexey Svyatkovskiy Shengyu Fu Michele Tufano Shao\u00a0Kun Deng Colin\u00a0B. Clement Dawn Drain Neel Sundaresan Jian Yin Daxin Jiang and Ming Zhou. 2020. GraphCodeBERT: Pre-training Code Representations with Data Flow. CoRR abs\/2009.08366(2020). arXiv:2009.08366https:\/\/arxiv.org\/abs\/2009.08366  Daya Guo Shuo Ren Shuai Lu Zhangyin Feng Duyu Tang Shujie Liu Long Zhou Nan Duan Alexey Svyatkovskiy Shengyu Fu Michele Tufano Shao\u00a0Kun Deng Colin\u00a0B. Clement Dawn Drain Neel Sundaresan Jian Yin Daxin Jiang and Ming Zhou. 2020. GraphCodeBERT: Pre-training Code Representations with Data Flow. CoRR abs\/2009.08366(2020). arXiv:2009.08366https:\/\/arxiv.org\/abs\/2009.08366"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/DLS51937.2020.00008"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_15_1","unstructured":"Huggingface.co. 2020. Tokenizer summary. https:\/\/huggingface.co\/transformers\/v3.0.2\/tokenizer_summary.html  Huggingface.co. 2020. Tokenizer summary. https:\/\/huggingface.co\/transformers\/v3.0.2\/tokenizer_summary.html"},{"key":"e_1_3_2_1_16_1","unstructured":"Hamel Husain Ho-Hsiang Wu Tiferet Gazit Miltiadis Allamanis and Marc Brockschmidt. 2019. CodeSearchNet Challenge: Evaluating the State of Semantic Code Search. CoRR abs\/1909.09436(2019). arXiv:1909.09436http:\/\/arxiv.org\/abs\/1909.09436  Hamel Husain Ho-Hsiang Wu Tiferet Gazit Miltiadis Allamanis and Marc Brockschmidt. 2019. CodeSearchNet Challenge: Evaluating the State of Semantic Code Search. CoRR abs\/1909.09436(2019). arXiv:1909.09436http:\/\/arxiv.org\/abs\/1909.09436"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.62"},{"key":"e_1_3_2_1_18_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. CoRR abs\/1910.13461(2019). arXiv:1910.13461http:\/\/arxiv.org\/abs\/1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis , Yinhan Liu , Naman Goyal , Marjan Ghazvininejad , Abdelrahman Mohamed , Omer Levy , Veselin Stoyanov , and Luke Zettlemoyer . 2019 . BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. CoRR abs\/1910.13461(2019). arXiv:1910.13461http:\/\/arxiv.org\/abs\/1910.13461 Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2019. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. CoRR abs\/1910.13461(2019). arXiv:1910.13461http:\/\/arxiv.org\/abs\/1910.13461"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10051692"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3076142"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2991079.2991102"},{"key":"e_1_3_2_1_22_1","volume-title":"SySeVR: A framework for using deep learning to detect software vulnerabilities","author":"Li Zhen","year":"2021","unstructured":"Zhen Li , Deqing Zou , Shouhuai Xu , Hai Jin , Yawei Zhu , and Zhaoxuan Chen . 2021. SySeVR: A framework for using deep learning to detect software vulnerabilities . IEEE Trans. Dependable Sec. Comput( 2021 ). https:\/\/doi.org\/abs\/1807.06756 Zhen Li, Deqing Zou, Shouhuai Xu, Hai Jin, Yawei Zhu, and Zhaoxuan Chen. 2021. SySeVR: A framework for using deep learning to detect software vulnerabilities. IEEE Trans. Dependable Sec. Comput(2021). https:\/\/doi.org\/abs\/1807.06756"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23158"},{"key":"e_1_3_2_1_24_1","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692(2019). arxiv:1907.11692http:\/\/arxiv.org\/abs\/1907.11692  Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692(2019). arxiv:1907.11692http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_25_1","unstructured":"Microsoft. 2022. DeepSpeed. https:\/\/www.deepspeed.ai.  Microsoft. 2022. DeepSpeed. https:\/\/www.deepspeed.ai."},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. NDSS.","author":"Newsome James","year":"2005","unstructured":"James Newsome and Dawn Song . 2005 . Dynamic Taint Analysis for Automatic Detection, Analysis, and Signature Generation of Exploits on Commodity Software . In Proc. NDSS. James Newsome and Dawn Song. 2005. Dynamic Taint Analysis for Automatic Detection, Analysis, and Signature Generation of Exploits on Commodity Software. In Proc. NDSS."},{"key":"e_1_3_2_1_27_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving Language Understanding by Generative Pre-Training. https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf.  Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving Language Understanding by Generative Pre-Training. https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf."},{"key":"e_1_3_2_1_28_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019). https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf.  Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019). https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00349"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00120"},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. EMC2","author":"Sanh Victor","unstructured":"Victor Sanh , Lysandre Debut , Julien Chaumond , and Thomas Wolf . 2019. DistilBERT , a distilled version of BERT: smaller, faster, cheaper and lighter . In Proc. EMC2 : 5 th Edition Co-located with NeurIPS\u2019 19. 1\u20135. Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. In Proc. EMC2: 5th Edition Co-located with NeurIPS\u201919. 1\u20135.","edition":"5"},{"key":"e_1_3_2_1_32_1","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arxiv:1909.08053\u00a0[cs.CL]  Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arxiv:1909.08053\u00a0[cs.CL]"},{"key":"e_1_3_2_1_33_1","volume-title":"Fuzzing: Brute Force Vulnerability Discovery. Pearson Education","author":"Sutton Michael","year":"2007","unstructured":"Michael Sutton , Adam Greene , and Pedram Amini . 2007 . Fuzzing: Brute Force Vulnerability Discovery. Pearson Education (2007). Michael Sutton, Adam Greene, and Pedram Amini. 2007. Fuzzing: Brute Force Vulnerability Discovery. Pearson Education (2007)."},{"key":"e_1_3_2_1_34_1","volume-title":"TIOBE Index for","author":"\u00a0company TIOBE.","year":"2022","unstructured":"the software quality \u00a0company TIOBE. 2022. TIOBE Index for May 2022 . https:\/\/www.tiobe.com\/tiobe-index\/ the software quality\u00a0company TIOBE. 2022. TIOBE Index for May 2022. https:\/\/www.tiobe.com\/tiobe-index\/"},{"key":"e_1_3_2_1_35_1","volume-title":"Proc. Advances in neural information processing systems, Vol.\u00a030","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan\u00a0 N Gomez , \u0141ukasz Kaiser , and Illia Polosukhin . 2017 . Attention is all you need . In Proc. Advances in neural information processing systems, Vol.\u00a030 . Curran Associates, Inc., 5998\u20136008. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proc. Advances in neural information processing systems, Vol.\u00a030. Curran Associates, Inc., 5998\u20136008."},{"key":"e_1_3_2_1_36_1","unstructured":"VULDB. 2020. Apple macOS USD File buffer overflow. https:\/\/vuldb.com\/?id.163591  VULDB. 2020. Apple macOS USD File buffer overflow. https:\/\/vuldb.com\/?id.163591"},{"key":"e_1_3_2_1_37_1","unstructured":"VULDB. 2020. Facebook WhatsApp on Android Video Stream buffer overflow. https:\/\/vuldb.com\/?id.160672  VULDB. 2020. Facebook WhatsApp on Android Video Stream buffer overflow. https:\/\/vuldb.com\/?id.160672"},{"key":"e_1_3_2_1_38_1","unstructured":"VULDB. 2021. NVIDIA Shield TV up to 8.2.1 NVDEC buffer overflow. https:\/\/vuldb.com\/?id.168508  VULDB. 2021. NVIDIA Shield TV up to 8.2.1 NVDEC buffer overflow. https:\/\/vuldb.com\/?id.168508"},{"key":"e_1_3_2_1_39_1","unstructured":"VulDeePecker. 2018. Database of \"VulDeePecker A Deep Learning-Based System for Vulnerability Detection\". https:\/\/github.com\/CGCL-codes\/VulDeePecker  VulDeePecker. 2018. Database of \"VulDeePecker A Deep Learning-Based System for Vulnerability Detection\". https:\/\/github.com\/CGCL-codes\/VulDeePecker"},{"key":"e_1_3_2_1_40_1","unstructured":"David\u00a0A. Wheeler. 2018. Flawfinder. https:\/\/dwheeler.com\/flawfinder\/.  David\u00a0A. Wheeler. 2018. Flawfinder. https:\/\/dwheeler.com\/flawfinder\/."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2014.44"},{"key":"e_1_3_2_1_42_1","volume-title":"Proc. NeurIPS.","author":"Zhou Yaqin","year":"2019","unstructured":"Yaqin Zhou , Shangqing Liu , Jingkai Siow , Xiaoning Du , and Yang Liu . 2019 . Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks . In Proc. NeurIPS. Yaqin Zhou, Shangqing Liu, Jingkai Siow, Xiaoning Du, and Yang Liu. 2019. Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks. In Proc. NeurIPS."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Yukun Zhu Ryan Kiros Richard\u00a0S. Zemel Ruslan Salakhutdinov Raquel Urtasun Antonio Torralba and Sanja Fidler. 2015. Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books. CoRR abs\/1506.06724(2015). arXiv:1506.06724http:\/\/arxiv.org\/abs\/1506.06724  Yukun Zhu Ryan Kiros Richard\u00a0S. Zemel Ruslan Salakhutdinov Raquel Urtasun Antonio Torralba and Sanja Fidler. 2015. Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books. CoRR abs\/1506.06724(2015). arXiv:1506.06724http:\/\/arxiv.org\/abs\/1506.06724","DOI":"10.1109\/ICCV.2015.11"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Noah Ziems and Shaoen Wu. 2021. Security Vulnerability Detection Using Deep Learning Natural Language Processing. arxiv:2105.02388\u00a0[cs.CR]  Noah Ziems and Shaoen Wu. 2021. Security Vulnerability Detection Using Deep Learning Natural Language Processing. arxiv:2105.02388\u00a0[cs.CR]","DOI":"10.1109\/INFOCOMWKSHPS51825.2021.9484500"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2019.2942930"}],"event":{"name":"ACSAC: Annual Computer Security Applications Conference","location":"Austin TX USA","acronym":"ACSAC"},"container-title":["Proceedings of the 38th Annual Computer Security Applications Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3564625.3567985","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3564625.3567985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:12Z","timestamp":1750183752000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3564625.3567985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":45,"alternative-id":["10.1145\/3564625.3567985","10.1145\/3564625"],"URL":"https:\/\/doi.org\/10.1145\/3564625.3567985","relation":{},"subject":[],"published":{"date-parts":[[2022,12,5]]},"assertion":[{"value":"2022-12-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}