{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T22:39:33Z","timestamp":1730327973832,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1145\/3644815.3644958","type":"proceedings-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T17:28:38Z","timestamp":1718126918000},"page":"178-183","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ML-On-Rails: Safeguarding Machine Learning Models in Software Systems \u2014 A Case Study"],"prefix":"10.1145","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-9533-8896","authenticated-orcid":false,"given":"Hala","family":"Abdelkader","sequence":"first","affiliation":[{"name":"Applied Artificial Intelligence Institute, Deakin University, Victoria, Australia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3812-9785","authenticated-orcid":false,"given":"Mohamed","family":"Abdelrazek","sequence":"additional","affiliation":[{"name":"Applied Artificial Intelligence Institute, Deakin University, Victoria, Australia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3187-4937","authenticated-orcid":false,"given":"Scott","family":"Barnett","sequence":"additional","affiliation":[{"name":"Applied Artificial Intelligence Institute, Deakin University, Victoria, Australia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9827-5496","authenticated-orcid":false,"given":"Jean-Guy","family":"Schneider","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-2590-1185","authenticated-orcid":false,"given":"Priya","family":"Rani","sequence":"additional","affiliation":[{"name":"RMIT University, Melbourne, Australia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-4805-1467","authenticated-orcid":false,"given":"Rajesh","family":"Vasa","sequence":"additional","affiliation":[{"name":"Applied Artificial Intelligence Institute, Deakin University, Victoria, Australia"}]}],"member":"320","published-online":{"date-parts":[[2024,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. Adversarial Machine Learning. https:\/\/ibm.co\/36fhajg [Online]. Accessed on 2023-11-19."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. Responsible AI Practices. https:\/\/ai.google\/responsibilities\/responsible-ai-practices\/?category=security [Online]. Accessed on 2023-11-19."},{"key":"e_1_3_2_1_3_1","unstructured":"[n.d.]. Securing the Future of AI and ML at Microsoft. https:\/\/docs.microsoft.com\/en-us\/security\/securing-artificial-intelligence-machine-learning [Online]. Accessed on 2023-11-19."},{"key":"e_1_3_2_1_4_1","unstructured":"[n.d.]. Status codes in HTTP. https:\/\/www.iana.org\/assignments\/http-status-codes\/http-status-codes.xhtml Accessed on 2023-08-08."},{"key":"e_1_3_2_1_5_1","volume-title":"SSDPose: A Single Shot Deep Pose Estimation and Analysis. In 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC). IEEE","author":"Abobakr Ahmed","year":"2019","unstructured":"Ahmed Abobakr, Hala Abdelkader, Julie Iskander, Darius Nahavandi, Khaled Saleh, Mohamed Attia, Mohammed Hossny, and Saeid Nahavandi. 2019. SSDPose: A Single Shot Deep Pose Estimation and Analysis. In 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC). IEEE, 1862--1868."},{"volume-title":"Rgb-d fall detection via deep residual convolutional lstm networks. In 2018 Digital Image Computing: Techniques and Applications (DICTA)","author":"Abobakr Ahmed","key":"e_1_3_2_1_6_1","unstructured":"Ahmed Abobakr, Mohammed Hossny, Hala Abdelkader, and Saeid Nahavandi. 2018. Rgb-d fall detection via deep residual convolutional lstm networks. In 2018 Digital Image Computing: Techniques and Applications (DICTA). IEEE, 1--7."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00042"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2942288"},{"key":"e_1_3_2_1_9_1","volume-title":"The internal state of an llm knows when its lying. arXiv preprint arXiv:2304.13734","author":"Azaria Amos","year":"2023","unstructured":"Amos Azaria and Tom Mitchell. 2023. The internal state of an llm knows when its lying. arXiv preprint arXiv:2304.13734 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"ECIS","volume":"1","author":"Baier Lucas","year":"2019","unstructured":"Lucas Baier, Fabian J\u00f6hren, and Stefan Seebacher. 2019. Challenges in the Deployment and Operation of Machine Learning in Practice.. In ECIS, Vol. 1."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfop.2023.100005"},{"key":"e_1_3_2_1_12_1","volume-title":"Davide Del Testa","author":"Bojarski Mariusz","year":"2016","unstructured":"Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, et al. 2016. End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00175"},{"key":"e_1_3_2_1_15_1","volume-title":"Large language models improve Alzheimer's disease diagnosis using multi-modality data. arXiv preprint arXiv:2305.19280","author":"Feng Yingjie","year":"2023","unstructured":"Yingjie Feng, Jun Wang, Xianfeng Gu, Xiaoyin Xu, and Min Zhang. 2023. Large language models improve Alzheimer's disease diagnosis using multi-modality data. arXiv preprint arXiv:2305.19280 (2023)."},{"volume-title":"Deep learning","author":"Goodfellow Ian","key":"e_1_3_2_1_16_1","unstructured":"Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep learning. MIT press."},{"key":"e_1_3_2_1_17_1","volume-title":"Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion.2019.00115"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00080"},{"key":"e_1_3_2_1_20_1","volume-title":"Unsolved problems in ml safety. arXiv preprint arXiv:2109.13916","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Nicholas Carlini, John Schulman, and Jacob Steinhardt. 2021. Unsolved problems in ml safety. arXiv preprint arXiv:2109.13916 (2021)."},{"key":"e_1_3_2_1_21_1","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR."},{"key":"e_1_3_2_1_22_1","volume-title":"Misspelling Correction with Pre-trained Contextual Language Model. In 2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI* CC). IEEE Computer Society, 144--149","author":"Hu Yifei","year":"2020","unstructured":"Yifei Hu, Xiaonan Jing, Youlim Ko, and Julia Taylor Rayz. 2020. Misspelling Correction with Pre-trained Contextual Language Model. In 2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI* CC). IEEE Computer Society, 144--149."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11675"},{"key":"e_1_3_2_1_24_1","volume-title":"Exploiting programmatic behavior of llms: Dual-use through standard security attacks. arXiv preprint arXiv:2302.05733","author":"Kang Daniel","year":"2023","unstructured":"Daniel Kang, Xuechen Li, Ion Stoica, Carlos Guestrin, Matei Zaharia, and Tatsunori Hashimoto. 2023. Exploiting programmatic behavior of llms: Dual-use through standard security attacks. arXiv preprint arXiv:2302.05733 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPW50608.2020.00028"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3233\/IDT-190160"},{"key":"e_1_3_2_1_27_1","unstructured":"Shiyu Liang Yixuan Li and R Srikant. 2018. Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks. In ICLR."},{"key":"e_1_3_2_1_28_1","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume":"33","author":"Liu Weitang","year":"2020","unstructured":"Weitang Liu, Xiaoyun Wang, John Owens, and Yixuan Li. 2020. Energy-based out-of-distribution detection. Advances in Neural Information Processing Systems 33 (2020), 21464--21475.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"A unified approach to interpreting model predictions. Advances in neural information processing systems 30","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.84"},{"key":"e_1_3_2_1_31_1","volume-title":"Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. arXiv preprint arXiv:2303.08896","author":"Manakul Potsawee","year":"2023","unstructured":"Potsawee Manakul, Adian Liusie, and Mark JF Gales. 2023. Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. arXiv preprint arXiv:2303.08896 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the conference on fairness, accountability, and transparency. 220--229","author":"Wu Simone","year":"2019","unstructured":"MargaretMitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, and Timnit Gebru. 2019. Model cards for model reporting. In Proceedings of the conference on fairness, accountability, and transparency. 220--229."},{"key":"e_1_3_2_1_33_1","volume-title":"Leveraging Implicit Feedback from Deployment Data in Dialogue. arXiv preprint arXiv:2307.14117","author":"Pang Richard Yuanzhe","year":"2023","unstructured":"Richard Yuanzhe Pang, Stephen Roller, Kyunghyun Cho, He He, and Jason Weston. 2023. Leveraging Implicit Feedback from Deployment Data in Dialogue. arXiv preprint arXiv:2307.14117 (2023)."},{"key":"e_1_3_2_1_34_1","unstructured":"Baolin Peng Michel Galley Pengcheng He Hao Cheng Yujia Xie Yu Hu Qiuyuan Huang Lars Liden Zhou Yu Weizhu Chen et al. 2023. Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv preprint arXiv:2302.12813 (2023)."},{"key":"e_1_3_2_1_35_1","unstructured":"Stephan Rabanser Stephan G\u00fcnnemann and Zachary Lipton. 2019. Failing loudly: An empirical study of methods for detecting dataset shift. In Advances in Neural Information Processing Systems (NIPS). 1396--1408."},{"key":"e_1_3_2_1_36_1","volume-title":"About ml: Annotation and benchmarking on understanding and transparency of machine learning lifecycles. arXiv preprint arXiv:1912.06166","author":"Raji Inioluwa Deborah","year":"2019","unstructured":"Inioluwa Deborah Raji and Jingying Yang. 2019. About ml: Annotation and benchmarking on understanding and transparency of machine learning lifecycles. arXiv preprint arXiv:1912.06166 (2019)."},{"key":"e_1_3_2_1_37_1","volume-title":"NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails. arXiv preprint arXiv:2310.10501","author":"Rebedea Traian","year":"2023","unstructured":"Traian Rebedea, Razvan Dinu, Makesh Sreedhar, Christopher Parisien, and Jonathan Cohen. 2023. NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails. arXiv preprint arXiv:2310.10501 (2023)."},{"key":"e_1_3_2_1_38_1","first-page":"5","article-title":"On challenges in machine learning model management","volume":"41","author":"Schelter Sebastian","year":"2018","unstructured":"Sebastian Schelter, Felix Biessmann, Tim Januschowski, David Salinas, Stephan Seufert, Gyuri Szarvas, Manasi Vartak, Samuel Madden, Hui Miao, and Amol Deshpande. 2018. On challenges in machine learning model management. IEEE Data Engineering Bulletin 41, 4 (2018), 5--15.","journal-title":"IEEE Data Engineering Bulletin"},{"key":"e_1_3_2_1_39_1","volume-title":"Identifying and Extracting Rare Disease Phenotypes with Large Language Models. arXiv preprint arXiv:2306.12656","author":"Shyr Cathy","year":"2023","unstructured":"Cathy Shyr, Yan Hu, Paul A Harris, and Hua Xu. 2023. Identifying and Extracting Rare Disease Phenotypes with Large Language Models. arXiv preprint arXiv:2306.12656 (2023)."},{"key":"e_1_3_2_1_40_1","first-page":"144","article-title":"React: Out-of-distribution detection with rectified activations","volume":"34","author":"Sun Yiyou","year":"2021","unstructured":"Yiyou Sun, Chuan Guo, and Yixuan Li. 2021. React: Out-of-distribution detection with rectified activations. Advances in Neural Information Processing Systems 34 (2021), 144--157.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_40"},{"key":"e_1_3_2_1_42_1","volume-title":"2nd International Conference on Learning Representations, ICLR","author":"Szegedy Christian","year":"2014","unstructured":"Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2014. Intriguing properties of neural networks. In 2nd International Conference on Learning Representations, ICLR 2014."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180220"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-srw.6"},{"key":"e_1_3_2_1_45_1","volume-title":"Proc. 20th Machine Learning conference of Belgium and The Netherlands. 27--34","author":"Tromp Erik","year":"2011","unstructured":"Erik Tromp and Mykola Pechenizkiy. 2011. Graph-based n-gram language identification on short texts. In Proc. 20th Machine Learning conference of Belgium and The Netherlands. 27--34."},{"key":"e_1_3_2_1_46_1","volume-title":"Jailbroken: How does llm safety training fail? arXiv preprint arXiv:2307.02483","author":"Wei Alexander","year":"2023","unstructured":"Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2023. Jailbroken: How does llm safety training fail? arXiv preprint arXiv:2307.02483 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Generalized out-of-distribution detection: A survey. arXiv preprint arXiv:2110.11334","author":"Yang Jingkang","year":"2021","unstructured":"Jingkang Yang, Kaiyang Zhou, Yixuan Li, and Ziwei Liu. 2021. Generalized out-of-distribution detection: A survey. arXiv preprint arXiv:2110.11334 (2021)."},{"key":"e_1_3_2_1_48_1","unstructured":"Juexiao Zhou Xiaonan He Liyuan Sun Jiannan Xu Xiuying Chen Yuetan Chu Longxi Zhou Xingyu Liao Bin Zhang and Xin Gao. 2023. Skingpt-4: An interactive dermatology diagnostic system with visual large language model. (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043","author":"Zou Andy","year":"2023","unstructured":"Andy Zou, Zifan Wang, J Zico Kolter, and Matt Fredrikson. 2023. Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043 (2023)."}],"event":{"name":"CAIN 2024: IEEE\/ACM 3rd International Conference on AI Engineering - Software Engineering for AI","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Lisbon Portugal","acronym":"CAIN 2024"},"container-title":["Proceedings of the IEEE\/ACM 3rd International Conference on AI Engineering - Software Engineering for AI"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3644815.3644958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T17:51:53Z","timestamp":1718214713000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3644815.3644958"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":49,"alternative-id":["10.1145\/3644815.3644958","10.1145\/3644815"],"URL":"https:\/\/doi.org\/10.1145\/3644815.3644958","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]},"assertion":[{"value":"2024-06-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}