{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:03:29Z","timestamp":1780589009637,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":8,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1145\/3779208.3804880","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:21:58Z","timestamp":1780586518000},"page":"1880-1882","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["POSTER: Small but Secure: Distilling SecAlign Defense on Edge LLMs via On-Policy RL"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9327-6545","authenticated-orcid":false,"given":"Debasmita","family":"Dey","sequence":"first","affiliation":[{"name":"Techno Main Salt Lake, Kolkata, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2586-3520","authenticated-orcid":false,"given":"Arkajyoti","family":"Mitra","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Matthieu Geist, and Olivier Bachern.","author":"Agarwal Rishabh","year":"2024","unstructured":"Rishabh Agarwal, Nino Vieillard, Yongchao Zhou, Piotr Stanczyk, Sabela Ramos Garea, Matthieu Geist, and Olivier Bachern. 2024. On-policy distillation of language models: Learning from self-generated mistakes. In The twelfth international conference on learning representations."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3719027.3744836"},{"key":"e_1_3_2_1_3_1","first-page":"82895","article-title":"Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for 11m agents","volume":"37","author":"Debenedetti Edoardo","year":"2024","unstructured":"Edoardo Debenedetti, Jie Zhang, Mislav Balunovic, Luca Beurer-Kellner, Marc Fischer, and Florian Tram\u00e8r. 2024. Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for 11m agents. Advances in Neural Information Processing Systems 37 (2024), 82895\u201382920.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","first-page":"30039","article-title":"Alpacafarm: A simulation framework for methods that learn from human feedback","volume":"36","author":"Dubois Yann","year":"2023","unstructured":"Yann Dubois, Chen Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy S Liang, and Tatsunori B Hashimoto. 2023. Alpacafarm: A simulation framework for methods that learn from human feedback. Advances in Neural Information Processing Systems 36 (2023), 30039\u201330069.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv: 1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv: 1503.02531 (2015)."},{"key":"e_1_3_2_1_6_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.64434\/tml.20251026"},{"key":"e_1_3_2_1_8_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."}],"event":{"name":"ASIA CCS '26: ACM Asia Conference on Computer and Communications Security","location":"Bangalore India","acronym":"ASIA CCS '26","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the ACM Asia Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3779208.3804880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:41:42Z","timestamp":1780587702000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779208.3804880"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":8,"alternative-id":["10.1145\/3779208.3804880","10.1145\/3779208"],"URL":"https:\/\/doi.org\/10.1145\/3779208.3804880","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"2026-06-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}