{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T06:43:17Z","timestamp":1760078597094,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819530717","type":"print"},{"value":"9789819530724","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:00:00Z","timestamp":1760140800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:00:00Z","timestamp":1760140800000},"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\/978-981-95-3072-4_6","type":"book-chapter","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T06:21:25Z","timestamp":1760077285000},"page":"66-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Detection Method for\u00a0Prompt Injection by\u00a0Integrating Pre-trained Model and\u00a0Heuristic Feature Engineering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0816-742X","authenticated-orcid":false,"given":"Yi","family":"Ji","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7259-9321","authenticated-orcid":false,"given":"Runzhi","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4542-3037","authenticated-orcid":false,"given":"Baolei","family":"Mao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,11]]},"reference":[{"key":"6_CR1","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27730\u201327744 (2022)"},{"key":"6_CR2","unstructured":"Chowdhery, A., et\u00a0al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Huang, R., et al.: AudioGPT: understanding and generating speech, music, sound, and talking head. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 23802\u201323804 (2024)","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Kim, C.Y., Lee, C.P., Mutlu, B.: Understanding large-language model (LLM)-powered human-robot interaction. In: Proceedings of the 2024 ACM\/IEEE international conference on human-robot interaction, pp. 371\u2013380 (2024)","DOI":"10.1145\/3610977.3634966"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Das, B.C., Amini, M.H., Wu, Y.: Security and privacy challenges of large language models: a survey. ACM Comput. Surv. 57(6), 1\u201339 (2025)","DOI":"10.1145\/3712001"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., Zhang, Y.: A survey on large language model (LLM) security and privacy: the good, the bad, and the ugly. High-Confidence Comput. 100211 (2024)","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"6_CR7","unstructured":"OWASP Foundation: Owasp top 10 list for large language models (2024). https:\/\/owasp.org\/www-project-top-10-for-large-language-model-applications"},{"key":"6_CR8","unstructured":"Perez, F., Ribeiro, I.: Ignore previous prompt: attack techniques for language models. In: NeurIPS ML Safety Workshop (2022)"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Greshake, K., Abdelnabi, S., Mishra, S., Endres, C., Holz, T., Fritz, M.: Not what you\u2019ve signed up for: compromising real-world LLM-integrated applications with indirect prompt injection. In: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, pp. 79\u201390 (2023)","DOI":"10.1145\/3605764.3623985"},{"key":"6_CR10","unstructured":"Liu, Y., Jia, Y., Geng, R., Jia, J., Gong, N.Z.: Formalizing and benchmarking prompt injection attacks and defenses. In: 33rd USENIX Security Symposium (USENIX Security 24), pp. 1831\u20131847 (2024)"},{"key":"6_CR11","unstructured":"Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"6_CR12","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. In: Advances in Neural Information Processing Systems, vol. 36, pp. 53728\u201353741 (2023)"},{"key":"6_CR13","unstructured":"Blueteam AI. fmops\/distilbert-prompt-injection (2024). https:\/\/huggingface.co\/fmops\/distilbert-prompt-injection"},{"key":"6_CR14","unstructured":"ProtectAI.com. Fine-tuned deberta-v3-base for prompt injection detection (2024). https:\/\/huggingface.co\/ProtectAI\/deberta-v3-base-prompt-injection-v2"},{"key":"6_CR15","unstructured":"Shang, C., Goyal, A., Erdogan, L.E., Ijju, S.: Safeguard: a benchmark suite for evaluating attacks and defenses on LLM safety (2023). https:\/\/devpost.com\/software\/safeguard-a1hfp4"},{"key":"6_CR16","unstructured":"Li, H., Liu, X.: Injecguard: benchmarking and mitigating over-defense in prompt injection guardrail models. arXiv preprint arXiv:2410.22770 (2024)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Rahman, M.A., Shahriar, H., Wu, F., Cuzzocrea, A.: Applying pre-trained multilingual BERT in embeddings for improved malicious prompt injection attacks detection. In: 2024 2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things (AIBThings), pp. 1\u20137. IEEE (2024)","DOI":"10.1109\/AIBThings63359.2024.10863664"},{"key":"6_CR18","unstructured":"Chen, S., Piet, J., Sitawarin, C., et al.: StruQ: defending against prompt injection with structured queries. In: 34th USENIX Security Symposium (USENIX Security 25), pp. 2383\u20132400 (2025)"},{"key":"6_CR19","doi-asserted-by":"publisher","unstructured":"Piet, J., et al.: Jatmo: prompt injection defense by task-specific finetuning. In: European Symposium on Research in Computer Security, pp. 105\u2013124. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-70879-4_6","DOI":"10.1007\/978-3-031-70879-4_6"},{"key":"6_CR20","unstructured":"Phute, M., et al.: LLM self defense: by self examination, LLMs know they are being tricked. In: The Second Tiny Papers Track at ICLR 2024 (2024)"},{"issue":"12","key":"6_CR21","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1038\/s42256-023-00765-8","volume":"5","author":"Y Xie","year":"2023","unstructured":"Xie, Y., et al.: Defending ChatGPT against jailbreak attack via self-reminders. Nat. Mach. Intell. 5(12), 1486\u20131496 (2023)","journal-title":"Nat. Mach. Intell."},{"key":"6_CR22","unstructured":"Anil, C., et al.: Many-shot jailbreaking. In: Advances in Neural Information Processing Systems, vol. 37, pp. 129696\u2013129742 (2025)"},{"key":"6_CR23","unstructured":"Bhatt, M., et\u00a0al.: Cyberseceval 2: a wide-ranging cybersecurity evaluation suite for large language models. arXiv preprint arXiv:2404.13161 (2024)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3072-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T06:21:32Z","timestamp":1760077292000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3072-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,11]]},"ISBN":["9789819530717","9789819530724"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3072-4_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,11]]},"assertion":[{"value":"11 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"4 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2025.scimeeting.cn\/en\/web\/index\/27434","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}