原创力文档人工智能论文英文版-Joint-GCG：Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems.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
Joint-GCG:UnifiedGradient-BasedPoisoningAttacksonRetrieval-Augmented
GenerationSystems
††∗∗
HaoweiWang,RupengZhang,JunjieWang,MingyangLi,
∗
YuekaiHuang,DandanWang,andQingWang
StateKeyLaboratoryofIntelligentGame,Beijing,China
InstituteofSoftware,ChineseAcademyofSciences,Beijing,China
UniversityofChineseAcademyofSciences,Beijing,China
5†Theseauthorscontributedequallytothiswork.∗Correspondingauthors.
2Email:{wanghaowei2023,zhangrupeng2023,junjie,mingyang2017,dandan}@
0
2
nAbstract—Retrieval-AugmentedGeneration(RAG)systemsen-However,thisremarkablepowercomeswithacritical
uhanceLargeLanguageModels(LLMs)byretrievingrelevantvulnerability:relianceonexternalcorporaintroducestherisk
Jdocumentsfromexternalcorporabeforegeneratingresponses.ofcorpuspoisoning[11],[12],[13],[14],[15].Asillustrated
6ThisapproachsignificantlyexpandsLLMcapabilitiesbyinFigure1,corpuspoisoninginvolvesmaliciousactors
leveragingvast,up-to-dateexternalknowledge.However,thisinjectingcraftedpoisoneddocumentsintotheknowledge
]relianceonexternalknowledgemakesRAGsystemsvulnerablebase.Ifretrievedandprocessed,thesepoisoneddocuments
Rtocorpuspoi
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-Decomposability-Guaranteed Cooperative Coevolution for Large-Scale Itinerary Planning.pdf
- 人工智能论文英文版-Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction.pdf
- 人工智能论文英文版-Towards an Explainable Comparison and Alignment of Feature Embeddings.pdf
- 人工智能论文英文版-Towards Lifecycle Unlearning Commitment Management：Measuring Sample-level Unlearning Completeness.pdf
- 人工智能论文英文版-Text-to-LoRA： Instant Transformer Adaption.pdf
- 人工智能论文英文版-PUZZLEWORLD：A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts.pdf
- 人工智能论文英文版-Microgrids Coalitions for Energy Market Balancing.pdf
- 人工智能论文英文版-BUILDING MODELS OF NEUROLOGICAL LANGUAGE.pdf
- 人工智能论文英文版-Hey, That’s My Data! Label-Only Dataset Inference in Large Language Models.pdf
- 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.pdf
文档评论（0）