Pub Date : 2024-12-01Epub Date: 2025-03-11DOI: 10.1109/globecom52923.2024.10901426
Youxiang Zhu, Ning Gao, Xiaohui Liang, Honggang Zhang
Online Large Language Models (LLMs) are widely employed across various tasks, including privacy-sensitive ones like financial advice or paragraph rewriting. Presently, users directly submit prompts to online LLM servers, inadvertently revealing sensitive keywords and facilitating server tracking to build user profiles. In this paper, we propose a local privacy-preserving prompt assistant (LPPA) that provides users with a usable method to balance privacy in the prompts and the utility of the LLM output. The LPPA will analyze the users' prompts, suggest modifying the prompts to protect the sensitive keywords, and provide an inference of the potential utility impact of the online LLM output. Specifically, we first propose a privacy module to identify the sensitive keywords in the prompt and adopt four privacy techniques, including remove, mask, replace, and rewrite to hide the keywords. While these techniques affect the utility of online LLM output, we measure such impact using the LLM output of the original prompt and modified prompts and discuss the cases with high, median, and low impact. In addition, we propose a utility inference model to infer the utility impact locally without disclosing the prompts to the online LLM. We evaluated LPPA on the real-world users' prompts and showed that the remove technique achieves the best performance, and it empowers users with meaningful ways to adjust their prompts to safeguard their privacy while still maintaining a satisfactory level of utility in online LLM usage.
{"title":"Exploiting Privacy Preserving Prompt Techniques for Online Large Language Model Usage.","authors":"Youxiang Zhu, Ning Gao, Xiaohui Liang, Honggang Zhang","doi":"10.1109/globecom52923.2024.10901426","DOIUrl":"10.1109/globecom52923.2024.10901426","url":null,"abstract":"<p><p>Online Large Language Models (LLMs) are widely employed across various tasks, including privacy-sensitive ones like financial advice or paragraph rewriting. Presently, users directly submit prompts to online LLM servers, inadvertently revealing sensitive keywords and facilitating server tracking to build user profiles. In this paper, we propose a local privacy-preserving prompt assistant (LPPA) that provides users with a usable method to balance privacy in the prompts and the utility of the LLM output. The LPPA will analyze the users' prompts, suggest modifying the prompts to protect the sensitive keywords, and provide an inference of the potential utility impact of the online LLM output. Specifically, we first propose a privacy module to identify the sensitive keywords in the prompt and adopt four privacy techniques, including remove, mask, replace, and rewrite to hide the keywords. While these techniques affect the utility of online LLM output, we measure such impact using the LLM output of the original prompt and modified prompts and discuss the cases with high, median, and low impact. In addition, we propose a utility inference model to infer the utility impact locally without disclosing the prompts to the online LLM. We evaluated LPPA on the real-world users' prompts and showed that the remove technique achieves the best performance, and it empowers users with meaningful ways to adjust their prompts to safeguard their privacy while still maintaining a satisfactory level of utility in online LLM usage.</p>","PeriodicalId":72021,"journal":{"name":"... IEEE Global Communications Conference. IEEE Global Communications Conference","volume":"2024 ","pages":"4304-4309"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12439101/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145082520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-04DOI: 10.1109/gcwkshps56602.2022.10008686
N. Fonseca, José Roberto B. da Marca, S. Bregni, L. Granville
{"title":"IEEE GLOBECOM 2022 General Chair Welcome Message","authors":"N. Fonseca, José Roberto B. da Marca, S. Bregni, L. Granville","doi":"10.1109/gcwkshps56602.2022.10008686","DOIUrl":"https://doi.org/10.1109/gcwkshps56602.2022.10008686","url":null,"abstract":"","PeriodicalId":72021,"journal":{"name":"... IEEE Global Communications Conference. IEEE Global Communications Conference","volume":"74 1","pages":"1"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74567141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-04DOI: 10.1109/globecom48099.2022.10000680
F. Granelli
{"title":"Message from the Technical Program Committee Chair","authors":"F. Granelli","doi":"10.1109/globecom48099.2022.10000680","DOIUrl":"https://doi.org/10.1109/globecom48099.2022.10000680","url":null,"abstract":"","PeriodicalId":72021,"journal":{"name":"... IEEE Global Communications Conference. IEEE Global Communications Conference","volume":"69 1","pages":"1"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77677844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-04DOI: 10.1109/globecom48099.2022.10001734
Faissal El Bouanani
{"title":"Operations Committee","authors":"Faissal El Bouanani","doi":"10.1109/globecom48099.2022.10001734","DOIUrl":"https://doi.org/10.1109/globecom48099.2022.10001734","url":null,"abstract":"","PeriodicalId":72021,"journal":{"name":"... IEEE Global Communications Conference. IEEE Global Communications Conference","volume":"8 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80482038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1109/GCWkshps56602.2022.10008736
R. Renna, R. D. Lamare
{"title":"Adaptive LLR-based APs selection for Grant-Free Random Access in Cell-Free Massive MIMO","authors":"R. Renna, R. D. Lamare","doi":"10.1109/GCWkshps56602.2022.10008736","DOIUrl":"https://doi.org/10.1109/GCWkshps56602.2022.10008736","url":null,"abstract":"","PeriodicalId":72021,"journal":{"name":"... IEEE Global Communications Conference. IEEE Global Communications Conference","volume":"19 3","pages":"196-201"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72461616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1109/GLOBECOM48099.2022.10001436
Alex Medeiros de Araújo, Anderson Bergamini de Neira, M. N. Lima
{"title":"Lifelong Autonomous Botnet Detection","authors":"Alex Medeiros de Araújo, Anderson Bergamini de Neira, M. N. Lima","doi":"10.1109/GLOBECOM48099.2022.10001436","DOIUrl":"https://doi.org/10.1109/GLOBECOM48099.2022.10001436","url":null,"abstract":"","PeriodicalId":72021,"journal":{"name":"... IEEE Global Communications Conference. IEEE Global Communications Conference","volume":"42 1","pages":"3742-3747"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85179121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1109/GLOBECOM48099.2022.10001523
Rodrigo A. C. da Silva, N. Fonseca
{"title":"Design of fog computing infrastructures with rotary-wing UAVs","authors":"Rodrigo A. C. da Silva, N. Fonseca","doi":"10.1109/GLOBECOM48099.2022.10001523","DOIUrl":"https://doi.org/10.1109/GLOBECOM48099.2022.10001523","url":null,"abstract":"","PeriodicalId":72021,"journal":{"name":"... IEEE Global Communications Conference. IEEE Global Communications Conference","volume":"69 1","pages":"5789-5794"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89076674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Image of Africa in Ghana’s Press is a comprehensive and highly analytical study of the impact of foreign news organisations on the creation of an image of Africa in its own press. Identifying a problematic focus on the Western media in previous studies of the African media image, Serwornoo uses the Ghanaian press as a case study to explore the effects of centuries of Afro-pessimistic discourse in the foreign press on the continent’s self-description.
{"title":"The Image of Africa in Ghana’s Press","authors":"M. Serwornoo","doi":"10.11647/obp.0227","DOIUrl":"https://doi.org/10.11647/obp.0227","url":null,"abstract":"The Image of Africa in Ghana’s Press is a comprehensive and highly analytical study of the impact of foreign news organisations on the creation of an image of Africa in its own press. Identifying a problematic focus on the Western media in previous studies of the African media image, Serwornoo uses the Ghanaian press as a case study to explore the effects of centuries of Afro-pessimistic discourse in the foreign press on the continent’s self-description.","PeriodicalId":72021,"journal":{"name":"... IEEE Global Communications Conference. IEEE Global Communications Conference","volume":"112 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80669422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-01DOI: 10.1109/GLOBECOM42002.2020.9322634
Tomaso de Cola
Future space missions are expected to implement a fully compliant CCSDS-DTN protocol stack in order to exploit the intrinsic store-forward capabilities. DTN technology, however, is not aimed at providing ordered data delivery, which is instead delegated to the application layer. More recently, the DelayTolerant Payload Conditioning (DTPC) has been introduced into the DTN protocol suite in order to mitigate such a limitation, although its interactions with application layer and the rest of the CCSDS protocol stack are not completely understood. To this end, this paper proposes a theoretical model for thoroughly investigating the performance of file-based data transfer through a CCSDS-DTN protocol architecture. A qualitative performance analysis allowed to summarise some important findings about overall protocols’ configuration and the related impact on the overall system performance.
{"title":"Achieving Ordered Data Block Delivery in CCSDS-DTN Space Networks: a Case Study","authors":"Tomaso de Cola","doi":"10.1109/GLOBECOM42002.2020.9322634","DOIUrl":"https://doi.org/10.1109/GLOBECOM42002.2020.9322634","url":null,"abstract":"Future space missions are expected to implement a fully compliant CCSDS-DTN protocol stack in order to exploit the intrinsic store-forward capabilities. DTN technology, however, is not aimed at providing ordered data delivery, which is instead delegated to the application layer. More recently, the DelayTolerant Payload Conditioning (DTPC) has been introduced into the DTN protocol suite in order to mitigate such a limitation, although its interactions with application layer and the rest of the CCSDS protocol stack are not completely understood. To this end, this paper proposes a theoretical model for thoroughly investigating the performance of file-based data transfer through a CCSDS-DTN protocol architecture. A qualitative performance analysis allowed to summarise some important findings about overall protocols’ configuration and the related impact on the overall system performance.","PeriodicalId":72021,"journal":{"name":"... IEEE Global Communications Conference. IEEE Global Communications Conference","volume":"10 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74312753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号