{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T13:14:12Z","timestamp":1784207652057,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234349","type":"print"},{"value":"9789819234356","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3435-6_40","type":"book-chapter","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:26:06Z","timestamp":1784204766000},"page":"476-488","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AttnSafe: Detecting Potential Backdoors for LLM via Attention Anomaly Analysis"],"prefix":"10.1007","author":[{"given":"Leyao","family":"Bao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinran","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoyong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuesong","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"40_CR1","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"J Devlin","year":"2019","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"40_CR2","doi-asserted-by":"publisher","first-page":"47230","DOI":"10.1109\/ACCESS.2019.2909068","volume":"7","author":"T Gu","year":"2019","unstructured":"Gu, T., Liu, K., Dolan-Gavitt, B., Garg, S.: BadNets: evaluating backdooring attacks on deep neural networks. IEEE Access. 7, 47230\u201347244 (2019)","journal-title":"IEEE Access"},{"key":"40_CR3","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1145\/3485832.3485837","volume-title":"Proceedings of the 37th Annual Computer Security Applications Conference","author":"X Chen","year":"2021","unstructured":"Chen, X., et al.: BadNL: Backdoor attacks against NLP models with semantic-preserving improvements. In: Proceedings of the 37th Annual Computer Security Applications Conference, pp. 554\u2013569. ACM (2021)"},{"key":"40_CR4","first-page":"2298","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"K Kurita","year":"2020","unstructured":"Kurita, K., Michel, P., Neubig, G.: Weight poisoning attacks on pretrained models. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2298\u20132309. Association for Computational Linguistics (2020)"},{"key":"40_CR5","series-title":"Long Papers","first-page":"4873","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","author":"F Qi","year":"2021","unstructured":"Qi, F., Yao, Y., Xu, S., Liu, Z., Sun, M.: Turn the combination lock: Learnable textual backdoor attacks via word substitution. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing Long Papers, vol. 1, pp. 4873\u20134883. Association for Computational Linguistics (2021)"},{"key":"40_CR6","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1109\/SP.2019.00031","volume-title":"2019 IEEE Symposium on Security and Privacy (SP)","author":"B Wang","year":"2019","unstructured":"Wang, B., et al.: Neural cleanse: identifying and mitigating backdoor attacks in neural networks. In: 2019 IEEE Symposium on Security and Privacy (SP), pp. 707\u2013723. IEEE (2019)"},{"key":"40_CR7","first-page":"16482","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Y Dong","year":"2021","unstructured":"Dong, Y., et al.: Black-box detection of backdoor attacks with limited information and data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16482\u201316491. IEEE (2021)"},{"key":"40_CR8","unstructured":"Yuan, D., Wei, S., Zhang, M., Liu, L., Wu, B.: Activation gradient based poisoned sample detection against backdoor attacks (2023). arXiv preprint https:\/\/arxiv.org\/abs\/2312.06230"},{"key":"40_CR9","unstructured":"Chen, X., Liu, C., Li, B., Lu, K., Song, D.: Targeted backdoor attacks on deep learning systems using data poisoning (2017). arXiv preprint https:\/\/arxiv.org\/abs\/1712.05526"},{"key":"40_CR10","first-page":"16463","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Y Li","year":"2021","unstructured":"Li, Y., Li, Y., Wu, B., Li, L., He, R., Lyu, S.: Invisible backdoor attack with sample-specific triggers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16463\u201316472. IEEE (2021)"},{"key":"40_CR11","first-page":"3454","volume":"33","author":"TA Nguyen","year":"2020","unstructured":"Nguyen, T.A., Tran, A.: Input-aware dynamic backdoor attack. Adv. Neural Inf. Proces. Syst. 33, 3454\u20133464 (2020)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"40_CR12","volume-title":"Clean-Label Backdoor Attacks","author":"A Turner","year":"2018","unstructured":"Turner, A., Tsipras, D., Madry, A.: Clean-Label Backdoor Attacks (2018). https:\/\/openreview.net\/forum?id=HJg6e2CcK7. Accessed 6 Jan 2026"},{"key":"40_CR13","volume-title":"Proceedings of the 25th Annual Network and Distributed System Security Symposium (NDSS 2018)","author":"Y Liu","year":"2018","unstructured":"Liu, Y., et al.: Trojaning attack on neural networks. In: Proceedings of the 25th Annual Network and Distributed System Security Symposium (NDSS 2018). Internet Society (2018)"},{"key":"40_CR14","unstructured":"Chen, B., et al.: Detecting backdoor attacks on deep neural networks by activation clustering (2018). arXiv preprint https:\/\/arxiv.org\/abs\/1811.03728"},{"key":"40_CR15","first-page":"8011","volume-title":"Advances in Neural Information Processing Systems 31 (NeurIPS 2018)","author":"B Tran","year":"2018","unstructured":"Tran, B., Li, J., Madry, A.: Spectral signatures in backdoor attacks. In: Advances in Neural Information Processing Systems 31 (NeurIPS 2018), vol. 31, pp. 8011\u20138021 (2018)"},{"key":"40_CR16","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1145\/3359789.3359790","volume-title":"Proceedings of the 35th Annual Computer Security Applications Conference","author":"Y Gao","year":"2019","unstructured":"Gao, Y., Xu, C., Wang, D., Chen, S., Ranasinghe, D.C., Nepal, S.: STRIP: a defence against Trojan attacks on deep neural networks. In: Proceedings of the 35th Annual Computer Security Applications Conference, pp. 113\u2013125. ACM (2019)"},{"key":"40_CR17","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1109\/ICDM50108.2020.00025","volume-title":"2020 IEEE International Conference on Data Mining (ICDM)","author":"W Guo","year":"2020","unstructured":"Guo, W., Wang, L., Xu, Y., Xing, X., Du, M., Song, D.: Towards inspecting and eliminating Trojan backdoors in deep neural networks. In: 2020 IEEE International Conference on Data Mining (ICDM), pp. 162\u2013171. IEEE (2020)"},{"key":"40_CR18","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1145\/3319535.3363216","volume-title":"Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Lee, W.C., Tao, G., Ma, S., Aafer, Y., Zhang, X.: ABS: scanning neural networks for back-doors by artificial brain stimulation. In: Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, pp. 1265\u20131282. ACM (2019)"},{"key":"40_CR19","first-page":"301","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S Kolouri","year":"2020","unstructured":"Kolouri, S., Saha, A., Pirsiavash, H., Hoffmann, H.: Universal litmus patterns: revealing backdoor attacks in CNNs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 301\u2013310. IEEE (2020)"},{"key":"40_CR20","first-page":"273","volume-title":"International Symposium on Research in Attacks, Intrusions, and Defenses","author":"K Liu","year":"2018","unstructured":"Liu, K., Dolan-Gavitt, B., Garg, S.: Fine-pruning: defending against backdooring attacks on deep neural networks. In: International Symposium on Research in Attacks, Intrusions, and Defenses, pp. 273\u2013294. Springer (2018)"},{"key":"40_CR21","first-page":"142","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"A Maas","year":"2011","unstructured":"Maas, A., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 142\u2013150. Association for Computational Linguistics (2011)"},{"key":"40_CR22","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.1145\/3460120.3485370","volume-title":"Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security","author":"L Shen","year":"2021","unstructured":"Shen, L., et al.: Backdoor pre-trained models can transfer to all. In: Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, pp. 3141\u20133158. ACM (2021)"},{"key":"40_CR23","doi-asserted-by":"publisher","first-page":"13189","DOI":"10.18653\/v1\/2024.emnlp-main.732","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Y Zeng","year":"2024","unstructured":"Zeng, Y., Sun, W., Huynh, T., Song, D., Li, B., Jia, R.: BEEAR: embedding-based adversarial removal of safety backdoors in instruction-tuned language models. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 13189\u201313215. Association for Computational Linguistics (2024)"},{"key":"40_CR24","doi-asserted-by":"publisher","first-page":"8365","DOI":"10.18653\/v1\/2021.emnlp-main.659","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"W Yang","year":"2021","unstructured":"Yang, W., Lin, Y., Li, P., Zhou, J., Sun, X.: RAP: robustness-aware perturbations for defending against backdoor attacks on NLP models. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 8365\u20138381. Association for Computational Linguistics (2021)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3435-6_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:26:11Z","timestamp":1784204771000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3435-6_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"ISBN":["9789819234349","9789819234356"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3435-6_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"assertion":[{"value":"17 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}