The deployment of Artificial Neural Networks (ANNs) in safety-critical applications poses a number of new verification and certification challenges. In particular, for ANN-enabled self-driving vehicles it is important to establish properties about the resilience of ANNs to noisy or even maliciously manipulated sensory input. We are addressing these challenges by defining resilience properties of ANN-based classifiers as the maximal amount of input or sensor perturbation which is still tolerated. This problem of computing maximal perturbation bounds for ANNs is then reduced to solving mixed integer optimization problems (MIP). A number of MIP encoding heuristics are developed for drastically reducing MIP-solver runtimes, and using parallelization of MIP-solvers results in an almost linear speed-up in the number (up to a certain limit) of computing cores in our experiments. We demonstrate the effectiveness and scalability of our approach by means of computing maximal resilience bounds for a number of ANN benchmark sets ranging from typical image recognition scenarios to the autonomous maneuvering of robots.
Image space formalism of convolutional neural networks for k-space interpolation
University of Würzburg(维尔茨堡大学);University Hospital Erlangen(埃尔朗根大学医院);Fraunhofer Institute for Integrated Circuits IIS(弗劳恩霍夫集成电路研究所);University Hospital Würzburg(维尔茨堡大学医院)
本文提出 RAKI 的图像空间形式化方法,通过激活掩码与雅可比矩阵解析分析 k 空间非线性激活对噪声传播和重建伪影的影响,实现 g 因子图的解析量化与噪声鲁棒性调控。
Adversarial AI in Insurance: Pervasiveness and Resilience
University of Torino(都灵大学);Collegio Carlo Alberto(卡洛·阿尔贝托学院);Reale Mutua Group(瑞莱穆图阿集团);KPA Group(KPA集团);Samuel Neaman Institute(塞缪尔·尼曼研究所);Technion(以色列理工学院)
Securing the Digital World: Protecting smart infrastructures and digital industries with Artificial Intelligence (AI)-enabled malware and intrusion detection
Smart Chest X-ray Worklist Prioritization using Artificial Intelligence: A Clinical Workflow Simulation
University Medical Center Hamburg-Eppendorf(汉堡-埃彭多夫大学医学中心);Hamburg University of Technology(汉堡工业大学);Forschungszentrum Medizintechnik Hamburg(汉堡医学技术研究中心);Philips Research(飞利浦研究院)
目的是评估人工智能(AI)的智能工作列表优先级是否可以优化放射学工作流程并减少胸部X光片(CXR)中关键发现的报告周转时间(RTAT)。此外,我们研究了一种方法来抵消人工智能的假阴性预测的影响-导致极端和危险的长RTAT,因为CXR被排序到工作列表的末尾。我们开发了一个模拟框架,该框架通过将医院特定的CXR生成率、报告率和病理分布结合起来,对大学医院的当前工作流程进行建模。使用它,我们模拟了标准的工作列表处理“先进先出”(FIFO),并将其与基于紧急程度的工作列表优先级进行了比较。由AI进行检查优先级排序,按紧急程度降序对8种不同的病理结果进行分类:气胸、胸腔积液、浸润、充血、肺不张、心脏肥大、肿块和异物。此外,我们还对最长等待时间设定了上限,超过这一上限,考试的紧急程度就最高。与FIFO模拟相比,所有优先级模拟中所有关键发现的平均RTAT均显著降低(例如,气胸:35.6 min vs. 80.1 min; p $<0.0001$),而大多数发现的最大RTAT同时增加(例如,气胸:1293 min vs. 890 min; p $<0.0001$)。我们的“上限”显著降低了所有类别的最大RTAT(例如,气胸:979 min vs. 1293 min / 1178 min; p $<0.0001$)。我们的模拟表明,人工智能的智能工作列表优先级可以降低CXR中关键发现的平均RTAT,…