Jove
Visualize
联系我们

相关实验视频

泄露:针对分割学习的多目标隐私窃取攻击.

Xiaoyang Xu, Wenzhe Yi, Juan Wang

    IEEE transactions on pattern analysis and machine intelligence
    |January 14, 2026
    PubMed
    概括
    此摘要是机器生成的。

    相关概念视频

    Survival Tree01:19

    Survival Tree

    388
    Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
     Building a Survival Tree
    Constructing a...
    388

    您也可能阅读

    相关文章

    通过共同作者、期刊和引用图与本文相关的文章。

    排序
    Same author

    The correlation between preoperative patellar tilt and clinical outcomes following unicompartmental knee arthroplasty.

    Journal of orthopaedic surgery and research·2026
    Same author

    First genome report of <i>Oudemansiella apalosarca</i> and comparative transcriptomics on fruiting body formation under different light conditions.

    Frontiers in fungal biology·2026
    Same author

    Optimization of biosynthesis process of bacterial cellulose membrane using seabuckthorn extract and its application in food preservation.

    International journal of biological macromolecules·2026
    Same author

    Staphylococcus aureus manipulates osteocytes to cause persistent chronic osteomyelitis and antibiotic resistance via pyroptosis pathway suppression.

    Drug resistance updates : reviews and commentaries in antimicrobial and anticancer chemotherapy·2025
    Same author

    Continuous Monitoring with AI-Enhanced BioMEMS Sensors: A Focus on Sustainable Energy Harvesting and Predictive Analytics.

    Micromachines·2025
    Same author

    Production of bacterial cellulose with high active components loading capacity for skin wound repair.

    International journal of biological macromolecules·2025
    Same journal

    TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

    IEEE transactions on pattern analysis and machine intelligence·2026
    查看所有相关文章
    JoVE
    x logofacebook logolinkedin logoyoutube logo
    关于 JoVE
    概览领导团队博客JoVE 帮助中心
    作者
    出版流程编辑委员会范围与政策同行评审常见问题投稿
    图书馆员
    用户评价订阅访问资源图书馆顾问委员会常见问题
    研究
    JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
    教育
    JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
    使用条款与条件
    隐私政策
    政策

    分拆学习 (SL) 易受隐私攻击的影响. 一个新的威胁,分泄漏 (SLeak),利用客户代表的偏好来窃取数据和功能,即使是有限的公共数据.

    科学领域:

    • 人工智能的人工智能
    • 机器学习安全 机器学习安全
    • 分布式系统 分布式系统

    背景情况:

    • 分拆学习 (SL) 提供了隐私和效率,但面临着推断攻击的风险.
    • 现有的SL隐私防御依赖于不切实际的假设,限制了现实世界的有效性.
    • 服务器对手可能会损害SL框架中的客户端隐私.

    研究的目的:

    • 调查分割学习 (SL) 框架中固有的漏洞.
    • 引入一种新的隐私威胁,分泄漏 (SLeak),针对SL.
    • 在没有强有力的隐私假设的情况下证明Sleak的有效性.

    主要方法:

    • 在SL的粉碎数据和服务器模型中分析客户代表偏好.
    • 开发一个替代客户端来模仿目标客户端的行为.
    • 为多个隐私目标引入分裂泄漏 (SLeak) 威胁.
    • 使用部分相同域的辅助公共数据进行攻击.

    主要成果:

    • 确定粉碎的数据和服务器模型都显示了客户代表偏好.
    • 证明替代客户端可以完美复制目标客户端的功能,数据和标签.
    • 与最先进的方法相比,Sleak攻击在各种数据集和模型中显示出更高的性能.

    相关实验视频

  • 废弃性研究证实了SLeak在各种场景中的稳定性和适用性.

    • 结论:

    • 分割学习 (SL) 具有固有的漏洞,可以被服务器对手利用.
    • 分裂泄漏 (SLeak) 是对SL隐私的实际和有效威胁.
    • 通过最小的数据要求,SLeak的成功突出了分布式学习中的重大隐私风险.