实时监控AI API使用量，智能预警防止天价账单，支持Claude等主流模型费用追踪与异常检测
IT之家 7 月 11 日消息，科技媒体 Wccftech 昨日（7 月 10 日）发布博文，报道称 一位韩国开发者收到来自 Anthropic 的 160 万美元、1662 万美元两笔扣款账单 ，但在 Claude API 控制台中显示为 0 美元。 博文指出该开发者于 7 月 8 日共收到 2 …
不用标注数据也能精准识别漏洞？ANVIL利用LLM的异常检测新范式，突破监督学习局限
arXiv:2408.16028v4 Announce Type: replace-cross Abstract: Supervised-learning-based vulnerability detectors often fall short due to limited labelled t…
提出智能体AI管道融合大语言模型，实现设备级能源异常检测与个性推荐，前沿技术落地场景。
arXiv:2606.28467v1 Announce Type: new Abstract: Appliance-level energy monitoring in office buildings produces noisy alerts that non-expert facility m…
用注意力机制检测野外恶意Agent技能，为AI安全提供新思路。
arXiv:2606.23416v1 Announce Type: cross Abstract: LLM agents increasingly load skills, file-based packages of natural-language instructions written by…
利用LLM检测希腊公共采购中的价格异常，一个案例揭露14.7万欧元的天价领带围巾采购，透明监管新利器。
Article URL: https://mizai.gr Comments URL: https://news.ycombinator.com/item?id=48574568 Points: 1 # Comments: 0
针对关系数据的异常检测新方法，填补图结构数据异常识别空白。
arXiv:2606.18621v1 Announce Type: new Abstract: Relational databases are widely used for managing structured data in real-world systems. Detecting ano…
挑战无监督异常检测中任务特定训练的必要性，揭示分布偏移下重建残差评分的局限性
arXiv:2601.22763v3 Announce Type: replace Abstract: Current state-of-the-art multi-class unsupervised anomaly detection (MUAD) methods rely on trainin…
利用大模型驱动行为并加入运动学约束，生成逼真的移动异常场景
arXiv:2606.10314v1 Announce Type: new Abstract: Although the study of human trajectory anomalies is critical for advancing spatial data mining, empiri…
用1.3B参数的GPT-Neo大模型结合创新的部分信用指数衰减位置感知强化学习微调，实现高精度实时日志异常检测。
arXiv:2606.08153v1 Announce Type: new Abstract: Detecting anomalies in large-scale system logs is critical for the reliability and security of modern …
利用机器学习对抗瞄准作弊，保护竞技公平与玩家体验
arXiv:2606.07650v1 Announce Type: cross Abstract: Multiplayer Online Games have become a multibillion dollar industry in the entertainment sector. How…
提出双特征解耦方法，专攻细粒度分布外检测难题，让模型精准识别细微异常。
arXiv:2606.05536v1 Announce Type: new Abstract: Out-of-distribution detection (OOD) is an indispensable technique when applying machine learning model…
新型激活级检测方法，在LLM代理输出前拦截凭证窃取，支持多轮对话防御。
arXiv:2606.04141v1 Announce Type: cross Abstract: LLM agents often place sensitive credentials in the same context window as untrusted retrieved conte…
将DMAIC质量管理模型融入LLM智能体，为工业异常检测提供可靠自动化方案，提升制造质量与安全。
arXiv:2606.04599v1 Announce Type: new Abstract: Large language model (LLM) agents have shown promise in automating complex data-analysis workflows, bu…
用大模型解读工业时空图，精准捕捉异常点，智能运维新利器
arXiv:2606.01691v1 Announce Type: cross Abstract: Industrial Internet systems face increasing threats from sophisticated industrial control system (IC…
用多模态大语言模型加强推理能力，实现更精准的时间序列异常检测，前沿思路值得关注。
arXiv:2602.08868v2 Announce Type: replace Abstract: Time-series anomaly detection (TSAD) with multimodal large language models (MLLMs) is an emerging …
利用多参考判决法审计巴利语到英语的LLM翻译，从异常值中挖掘系统错误，提升翻译评估精度。
arXiv:2606.01136v1 Announce Type: new Abstract: Single-score translation metrics can conflate legitimate variation with error, a problem especially ac…
无需预训练数据即可实现零样本时间序列异常检测，合成数据与相对上下文差异是关键创新。
arXiv:2509.21190v4 Announce Type: replace-cross Abstract: Time series anomaly detection (TSAD) is a critical task, but developing models that generali…
利用掩码扩散模型实现高效异常检测，创新结合生成与判别任务，适用于图像异常定位。
arXiv:2605.30046v1 Announce Type: cross Abstract: Anomaly detection aims to identify samples that deviate from the nominal data distribution and is ce…
无需训练即可实现零样本/少样本异常检测，智能体模型AnomalyAgent开辟新范式
arXiv:2605.30140v1 Announce Type: new Abstract: Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot an…
ICML 2026新研究，利用几何约束合成异常值，为异常检测提供高质量训练样本。
arXiv:2603.08413v2 Announce Type: replace-cross Abstract: Deep neural networks for image classification often exhibit overconfidence on out-of-distrib…