arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.04245cs.AI
收藏

VERIFAI:基于人工智能的系统设计和分析工具包

VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based Systems

University of California, Berkeley(加利福尼亚大学伯克利分校)

Tommaso Dreossi, Daniel J. Fremont, Shromona Ghosh, Edward Kim, Hadi Ravanbakhsh, Marcell Vazquez-Chanlatte, Sanjit A. Seshia

摘要:

我们提出了VERIFAI,一个软件工具包的正式设计和分析系统,包括人工智能(AI)和机器学习(ML)组件。VERIFAI特别寻求解决将形式化方法应用于感知和ML组件的挑战,包括基于神经网络的组件,并在存在环境不确定性的情况下建模和分析系统行为。我们描述了VERIFAI的初始版本,它集中在正式的模型和规范指导下的仿真。几个用例说明的例子,包括时间逻辑证伪,基于模型的系统模糊测试,参数合成,反例分析,和数据集增强。

英文摘要:

We present VERIFAI, a software toolkit for the formal design and analysis of systems that include artificial intelligence (AI) and machine learning (ML) components. VERIFAI particularly seeks to address challenges with applying formal methods to perception and ML components, including those based on neural networks, and to model and analyze system behavior in the presence of environment uncertainty. We describe the initial version of VERIFAI which centers on simulation guided by formal models and specifications. Several use cases are illustrated with examples, including temporal-logic falsification, model-based systematic fuzz testing, parameter synthesis, counterexample analysis, and data set augmentation.

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。

↑