arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1705.01040cs.LGcs.AIcs.LOcs.SE
收藏

人工神经网络的最大弹性

Maximum Resilience of Artificial Neural Networks

fortiss(fortiss研究所);Technische Universität München(慕尼黑工业大学)

Chih-Hong Cheng, Georg Nührenberg, Harald Ruess

摘要:

人工神经网络(ANN)在安全关键型应用中的部署带来了许多新的验证和认证挑战。特别是,对于支持ANN的自动驾驶车辆,重要的是要建立ANN对噪声甚至恶意操纵的感觉输入的弹性。我们通过将基于ANN的分类器的弹性属性定义为仍然可以容忍的最大输入量或传感器扰动来解决这些挑战。这个问题的计算最大扰动界的人工神经网络,然后减少到解决混合整数优化问题(MIP)。大量的MIP编码算法被开发用于大幅减少MIP求解器的运行时间,并且在我们的实验中,使用MIP求解器的并行化导致计算核心的数量(达到一定的限制)几乎线性加速。我们证明了我们的方法的有效性和可扩展性,通过计算的最大弹性范围的ANN基准集,从典型的图像识别场景的机器人的自主操纵。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑