{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T07:39:52Z","timestamp":1773041992306,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032018229","type":"print"},{"value":"9783032018236","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-01823-6_4","type":"book-chapter","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T19:14:23Z","timestamp":1761333263000},"page":"52-69","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Winning at\u00a0All Cost: A Small Environment for\u00a0Eliciting Specification Gaming Behaviors in\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Lars","family":"Malmqvist","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,25]]},"reference":[{"key":"4_CR1","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Man\u00e9, D.: Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)"},{"key":"4_CR2","unstructured":"Bondarenko, A., Volk, D., Volkov, D., Ladish, J.: Demonstrating specification gaming in reasoning models. arXiv preprint (2024)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L., Zaharia, M., Zou, J.: How is ChatGPT\u2019s behavior changing over time? Harvard Data Sci. Rev. 6(2) (2024)","DOI":"10.1162\/99608f92.5317da47"},{"key":"4_CR4","unstructured":"Clark, J., Amodei, D.: Faulty reward functions in the wild. OpenAI Blog (2016)"},{"issue":"9","key":"4_CR5","doi-asserted-by":"publisher","first-page":"2419","DOI":"10.1007\/s10994-021-05961-4","volume":"110","author":"G Dulac-Arnold","year":"2021","unstructured":"Dulac-Arnold, G., et al.: Challenges of real-world reinforcement learning: definitions, benchmarks and analysis. Mach. Learn. 110(9), 2419\u20132468 (2021)","journal-title":"Mach. Learn."},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Everitt, T., Lea, G., Hutter, M.: AGI safety literature review. arXiv preprint arXiv:1805.01109 (2018)","DOI":"10.24963\/ijcai.2018\/768"},{"key":"4_CR7","unstructured":"Greenblatt, R., et al.: Alignment faking in large language models. arXiv preprint arXiv:2412.14093 (2024)"},{"key":"4_CR8","unstructured":"Hubinger, E., et al.: Sleeper agents: training deceptive LLMs that persist through safety training. arXiv preprint arXiv:2401.05566 (2024)"},{"key":"4_CR9","unstructured":"Krakovna, V., et al.: Specification gaming: the flip side of AI ingenuity. DeepMind Blog (2020)"},{"issue":"2","key":"4_CR10","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1162\/artl_a_00319","volume":"26","author":"J Lehman","year":"2020","unstructured":"Lehman, J., et al.: The surprising creativity of digital evolution: a collection of anecdotes from the evolutionary computation and artificial life research communities. Artif. Life 26(2), 274\u2013306 (2020)","journal-title":"Artif. Life"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Malmqvist, L.: Sycophancy in large language models: causes and mitigations. arXiv preprint arXiv:2411.15287 (2024)","DOI":"10.1007\/978-3-031-92611-2_5"},{"key":"4_CR12","unstructured":"Meinke, A., Schoen, B., Scheurer, J., Balesni, M., Shah, R., Hobbhahn, M.: Frontier models are capable of in-context scheming. arXiv preprint arXiv:2412.04984 (2024)"},{"key":"4_CR13","unstructured":"METR: Evaluating frontier AI R &D capabilities of language model agents against human experts. METR Technical Report (2024)"},{"key":"4_CR14","unstructured":"Volkov, D.: LLM agent honeypot: monitoring AI hacking agents in the wild. arXiv preprint arXiv:2410.13919 (2024)"},{"key":"4_CR15","unstructured":"Scheurer, J., Balesni, M., Hobbhahn, M.: Large language models can strategically deceive their users when put under pressure. arXiv preprint arXiv:2311.07590 (2024)"},{"key":"4_CR16","unstructured":"Turtayev, R., Petrov, A., Volkov, D., Volk, D.: Hacking CTFs with plain agents. arXiv preprint arXiv:2412.02776 (2024)"},{"key":"4_CR17","unstructured":"Volkov, D.: Badllama 3: removing safety finetuning from Llama 3 in minutes. arXiv preprint arXiv:2407.01376 (2024)"},{"key":"4_CR18","unstructured":"van der Weij, T., Hofst\u00e4tter, F., Jaffe, O., Brown, S.F., Ward, F.R.: AI sandbagging: language models can strategically underperform on evaluations. arXiv preprint arXiv:2406.07358 (2024)"},{"issue":"6844","key":"4_CR19","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1038\/35085569","volume":"412","author":"CO Wilke","year":"2001","unstructured":"Wilke, C.O., Wang, J.L., Ofria, C., Lenski, R.E., Adami, C.: Evolution of digital organisms at high mutation rates leads to survival of the flattest. Nature 412(6844), 331\u2013333 (2001)","journal-title":"Nature"},{"key":"4_CR20","unstructured":"Yao, S., et al.: ReAct: synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2023)"}],"container-title":["Lecture Notes in Computer Science","Applied Cryptography and Network Security Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-01823-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T19:14:25Z","timestamp":1761333265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-01823-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,25]]},"ISBN":["9783032018229","9783032018236"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-01823-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,25]]},"assertion":[{"value":"25 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACNS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applied Cryptography and Network Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acns2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/acns2025.fordaysec.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}