ATLAS-AL:主动学习驱动的黑盒对抗样本搜索框架
Get the story
2026年10月7日,arXiv Machine Learning Theory(一手来源)发表论文,提出ATLAS(Adaptive Trust-Regions for Latent Adversarial Searches),一种面向黑盒学习系统的查询式框架。该方法将对抗样本生成问题转化为主动学习水平集估计问题,并结合校准近似与局部-全局采样架构,用于定位输入空间中的对抗区域。论文还提出基于主动学习的潜在对抗搜索自适应置信域方法。目前公开信息仅涉及该论文内容,未见后续实验验证或第三方复现报道。
Generated from reports · updated 3 hr ago
Timeline
Follow the coverage from different angles.
- arXiv · Machine Learning TheoryATLAS-AL:基于主动学习的潜在对抗搜索自适应置信域方法
论文提出 ATLAS(Adaptive Trust-Regions for Latent Adversarial Searches),一种面向黑盒学习系统的查询式框架,将对抗样本生成转化为主动学习水平集估计问题,并结合校准近似与局部-全局采样架构定位输入空间中的对抗区域。
Heat trend
Current heat 9·Comparable peak 10(Oct 7)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.