arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Joint Conference on Artificial Intelligence · 会议 · Artificial Intelligence

2026-08-04 至 2026-08-04 共收录 3
2608.00732 2026-08-04 cs.LG cs.CV 新提交

Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling

通过诱饵捷径与知识解耦缓解后门攻击

Zixuan Zhu, Rui Wang, Lihua Jing, Jinwen Zhong

机构 * Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所) School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)

AI总结 本研究提出TR防御方法,通过蜜罐捷径捕获后门知识,结合知识解耦策略与自动捷径生成,在四个基准数据集和五个模型架构上有效缓解多种后门攻击,同时保留良性性能。

Comments 19 pages; 11 figures; 14Tables; Accept by IJCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.30363 2026-08-04 q-fin.CP cs.AI cs.LG q-fin.ST 版本更新

Enhancing Regime Shift Detection Using Unstructured Data: A Study on the Treasury Market

利用非结构化数据增强制度转换检测:国债市场研究

Mingxuan Yi, Vidal Mehra, Jing Chen, John Cartlidge

机构 * School of Engineering Mathematics and Technology, University of Bristol, UK(布里斯托大学工程数学与技术学院) Propellant Digital B.V., Amsterdam, Netherlands(荷兰阿姆斯特丹Propellant Digital公司) School of Mathematics, Cardiff University, UK(卡迪夫大学数学学院)

AI总结 提出一种结合大语言模型推理与统计检验的文本增强型制度转换检测框架,在国债市场数据上实现F1=0.82,优于纯数据驱动方法。

Comments 9 pages, 4 figures. Selected for Long Oral presentation at the International Symposium on Large Language Models for Financial Services (FinLLM@IJCAI 2026), Bremen, Germany, 15 August 2026 (non-archival). Code available at: https://github.com/mingxuan-yi/regime_shift

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13077 2026-08-04 cs.MA cs.AI 版本更新

Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems

反事实推理在概率多智能体系统中的因果责任归因

Chunyan Mu, Muhammad Najib

机构 * University of Aberdeen(阿伯丁大学) Heriot-Watt University(赫瑞瓦特大学)

AI总结 本文提出基于反事实推理的因果责任归因方法,利用Shapley值确保公平性和一致性,构建了支持责任感知多智能体系统验证与策略推理的框架,并通过纳什均衡计算稳定策略配置。

Comments Accepted at IJCAI 2026. This is the full version containing all proofs

详情

展开后加载摘要…

URL PDF HTML 收藏