{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:29:24Z","timestamp":1787495364293,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819248049","type":"print"},{"value":"9789819248056","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"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\/978-981-92-4805-6_36","type":"book-chapter","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:46:50Z","timestamp":1787492810000},"page":"547-561","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VecTEE: Compact TEE Metadata Caching for Efficient Secure Vector Computing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0873-3471","authenticated-orcid":false,"given":"Husheng","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2370-0072","authenticated-orcid":false,"given":"Di","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4204-0686","authenticated-orcid":false,"given":"Tianyun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7727-440X","authenticated-orcid":false,"given":"Xinyao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8513-0792","authenticated-orcid":false,"given":"Jianan","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7603-4210","authenticated-orcid":false,"given":"Zidong","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9979-0561","authenticated-orcid":false,"given":"Xing","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2530-5874","authenticated-orcid":false,"given":"Qi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Abdullah, R., Zhou, H., Awad, A.: Plutus: bandwidth-efficient memory security for GPUs. In: Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 543\u2013555 (2023)","DOI":"10.1109\/HPCA56546.2023.10071100"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Akimoto, Y., Fukuchi, K., Akimoto, Y., Sakuma, J.: Privformer: privacy-preserving transformer with MPC. In: 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P), pp. 392\u2013410. IEEE (2023)","DOI":"10.1109\/EuroSP57164.2023.00031"},{"key":"36_CR3","unstructured":"Avazu: Avazu mobile ads CTR. https:\/\/www.kaggle.com\/c\/avazu-ctr-prediction"},{"issue":"2","key":"36_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3085572","volume":"14","author":"R Balasubramonian","year":"2017","unstructured":"Balasubramonian, R., Kahng, A.B., Muralimanohar, N., Shafiee, A., Srinivas, V.: Cacti 7: new tools for interconnect exploration in innovative off-chip memories. Trans. Archit. Code Optim. (TACO) 14(2), 1\u201325 (2017)","journal-title":"Trans. Archit. Code Optim. (TACO)"},{"key":"36_CR5","unstructured":"Costan, V., Devadas, S.: Intel SGX explained. Cryptology ePrint Archive (2016)"},{"key":"36_CR6","unstructured":"Criteo: Criteo display ad challenge. www.kaggle.com\/c\/criteo-display-ad-challenge"},{"key":"36_CR7","unstructured":"Criteo: Terabyte click logs. https:\/\/huggingface.co\/datasets\/criteo\/CriteoClickLogs"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Douze, M., et al.: The Faiss library. IEEE Trans. Big Data (2025)","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"36_CR9","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. arXiv preprint arXiv:2312.10997 (2023)"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Ghazi, B., et al.: Sparsity-preserving differentially private training of large embedding models. In: Proceedings of the Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/075280-0483"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Granlund, T., Montgomery, P.L.: Division by invariant integers using multiplication. In: Proceedings of the ACM SIGPLAN 1994 Conference on Programming Language Design and implementation, pp. 61\u201372 (1994)","DOI":"10.1145\/178243.178249"},{"issue":"6","key":"36_CR12","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/MSP.2016.124","volume":"14","author":"S Gueron","year":"2016","unstructured":"Gueron, S.: A memory encryption engine suitable for general purpose processors. IEEE Secur. Priv. 14(6), 54\u201362 (2016)","journal-title":"IEEE Secur. Priv."},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Hua, W., Umar, M., Zhang, Z., Suh, G.E.: MGX: near-zero overhead memory protection for data-intensive accelerators. In: Proceedings of the Annual International Symposium on Computer Architecture (ISCA), pp. 726\u2013741 (2022)","DOI":"10.1145\/3470496.3527418"},{"issue":"1","key":"36_CR14","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2010","unstructured":"Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. TPAMI 33(1), 117\u2013128 (2010)","journal-title":"TPAMI"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Jiao, D., et al.: Neo: towards efficient fully homomorphic encryption acceleration using tensor core. In: Proceedings of the 52nd Annual International Symposium on Computer Architecture, pp. 107\u2013121 (2025)","DOI":"10.1145\/3695053.3731408"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Jouppi, N., et al.: TPU v4: an optically reconfigurable supercomputer for machine learning with hardware support for embeddings. In: Proceedings of the Annual International Symposium on Computer Architecture (ISCA), pp. 1\u201314 (2023)","DOI":"10.1145\/3579371.3589350"},{"issue":"1","key":"36_CR17","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/LCA.2015.2414456","volume":"15","author":"Y Kim","year":"2015","unstructured":"Kim, Y., Yang, W., Mutlu, O.: Ramulator: a fast and extensible dram simulator. IEEE Comput. Archit. Lett. (CAL) 15(1), 45\u201349 (2015)","journal-title":"IEEE Comput. Archit. Lett. (CAL)"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, J., Na, S., Park, J., Huh, J.: TNPU: supporting trusted execution with tree-less integrity protection for neural processing unit. In: Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 229\u2013243 (2022)","DOI":"10.1109\/HPCA53966.2022.00025"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Accelerating personalized recommendation with cross-level near-memory processing. In: Proceedings of the Annual International Symposium on Computer Architecture (ISCA), pp. 1\u201313 (2023)","DOI":"10.1145\/3579371.3589101"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Mu, J., et al.: Alchemist: a unified accelerator architecture for cross-scheme fully homomorphic encryption. In: Proceedings of the 61st ACM\/IEEE Design Automation Conference, pp. 1\u20136 (2024)","DOI":"10.1145\/3649329.3657331"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Na, S., Lee, S., Kim, Y., Park, J., Huh, J.: Common counters: compressed encryption counters for secure GPU memory. In: Proceedings of the High-Performance Computer Architecture (HPCA), pp. 1\u201313 (2021)","DOI":"10.1109\/HPCA51647.2021.00011"},{"key":"36_CR22","unstructured":"Naumov, M., et al.: Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 (2019)"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Quinn, D., et al.: Accelerating retrieval-augmented generation. In: Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol. 1, pp. 15\u201332 (2025)","DOI":"10.1145\/3669940.3707264"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Shrivastava, N., Sarangi, S.R.: Securator: a fast and secure neural processing unit. In: Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 1127\u20131139 (2023)","DOI":"10.1109\/HPCA56546.2023.10071091"},{"key":"36_CR25","unstructured":"South, T., Zuskind, G., Mahari, R., Hardjono, T.: Secure community transformers: private pooled data for LLMs (2023)"},{"key":"36_CR26","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"36_CR27","unstructured":"Wang, Z., et al.: OPER: optimality-guided embedding table parallelization for large-scale recommendation model. In: Proceedings of the USENIX Annual Technical Conference (USENIX ATC), pp. 667\u2013682 (2024)"},{"key":"36_CR28","unstructured":"Watson, J.L., Wagh, S., Popa, R.A.: Piranha: a GPU platform for secure computation. In: USENIX Security Symposium (USENIX Security), pp. 827\u2013844 (2022)"},{"issue":"2","key":"36_CR29","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1145\/1150019.1136502","volume":"34","author":"C Yan","year":"2006","unstructured":"Yan, C., Englender, D., Prvulovic, M., Rogers, B., Solihin, Y.: Improving cost, performance, and security of memory encryption and authentication. ACM SIGARCH Comput. Archit. News 34(2), 179\u2013190 (2006)","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"36_CR30","unstructured":"Zheng, X., et al.: InputSnatch: stealing input in LLM services via timing side-channel attacks. arXiv preprint arXiv:2411.18191 (2024)"}],"container-title":["Lecture Notes in Computer Science","Advanced Parallel Processing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-4805-6_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:46:53Z","timestamp":1787492813000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-4805-6_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"ISBN":["9789819248049","9789819248056"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-4805-6_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"24 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APPT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Advanced Parallel Processing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brussels","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","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":"27 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"appt2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.appt-conference.com\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}