原创力文档人工智能论文英文版-SIMPLE YET EFFECTIVE：EXTRACTING PRIVATE DATA ACROSS CLIENTS IN FEDERATED FINE-TUNING OF LARGE LANGUAGE MODELS.pdfVIP
- 1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
- 2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击 这里二次下载。
- 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
- 4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
- 5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
- 6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 7、VIP文档为合作方或网友上传，每下载1次， 网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
SIMPLEYETEFFECTIVE:EXTRACTINGPRIVATEDATAACROSS
CLIENTSINFEDERATEDFINE-TUNINGOFLARGELANGUAGE
MODELS
APREPRINT
11234
YingqiHu,ZhuoZhang,JingyuanZhang,LizhenQu,ZenglinXu
1HarbinInstituteofTechnology2KuaishouTechnology
534
2MonashUniversityFudanUniversity
0huengchi@,iezhuo17@,jingyuanzhang@,
2Lizhen.Qu@,zenglinxu@
n
u
J
6ABSTRACT
]Federatedfine-tuningoflargelanguagemodels(FedLLMs)presentsapromisingapproachfor
Lachievingstrongmodelperformancewhilepreservingdataprivacyinsensitivedomains.However,
CtheinherentmemorizationabilityofLLMsmakesthemvulnerabletotrainingdataextractionattacks.
.Toinvestigatethisrisk,weintroducesimpleyeteffectiveextractionattackalgorithmsspecifically
s
cdesignedforFedLLMs.Incontrasttopriorverbatimextractionattacks,whichassumeaccessto
[fragmentsfromalltrainingdata,ourapproachoperatesunderamorerealisticthreatmodel,where
theattackeronlyhasaccesstoasingleclient’sdataandaimstoextractpreviouslyunseenpersonally
1identifiableinformation(PII)fromotherclients.Thisrequiresleveragingcontextualprefixesheldby
v
您可能关注的文档
- 人工智能论文英文版-Eigenspectrum Analysis of Neural Networks without Aspect Ratio.pdf
- 人工智能论文英文版-Cartridges：Lightweight and general-purpose long context.pdf
- 人工智能论文英文版-Distillation Robustifies Unlearning.pdf
- 人工智能论文英文版-PersonaAgent：When Large Language Model Agents Meet Personalization at Test Time.pdf
- 人工智能论文英文版-Reflect-then-Plan：Offline Model-Based Planning through a Doubly Bayesian Lens.pdf
- 人工智能论文英文版-DesignBench：A Comprehensive Benchmark for MLLM-based Front-end Code Generation.pdf
- 人工智能论文英文版-Visual Graph Arena： Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models.pdf
- 人工智能论文英文版-“We need to avail ourselves of [GenAI] to enhance knowledge distribution”： Empowering Older Adults through GenAI Literacy.pdf
- 人工智能论文英文版-GenIR： Generative Visual Feedback for Mental Image Retrieval.pdf
- 人工智能论文英文版-Integer Linear Programming Preprocessing for Maximum Satisfiability.pdf
- 人工智能论文英文版-FPDANet：A Multi-Section Classification Model for Intelligent Screening of Fetal Ultrasound.pdf
- 人工智能论文英文版-CP-Bench：Evaluating Large Language Models for Constraint Modelling.pdf
- 人工智能论文英文版-Astra：Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning.pdf
- 人工智能论文英文版-The Lock-in Hypothesis：Stagnation by Algorithm.pdf
- 人工智能论文英文版-TRUST：Test-time Resource Utilization for Superior Trustworthiness.pdf
- 人工智能论文英文版-When to Trust Context： Self-Reflective Debates for Context Reliability.pdf
- 人工智能论文英文版-Token Signature： Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models.pdf
- 人工智能论文英文版-Unlocking Recursive Thinking of LLMs：Alignment via Refinement.pdf
- 人工智能论文英文版-Leveraging Generative AI for Enhancing Automated Assessment in Programming Education Contests.pdf
- 人工智能论文英文版-AMPED：Adaptive Multi-objective Projection for balancing Exploration and skill Diversification.pdf
文档评论（0）