Adaptation 2.0: Adapting Specification Learners in Assured Adaptive Systems
Specification learning and controller synthesis are two methods that promise to provide control systems with assured adaptive capabilities at runtime. Specification learning can automatically update specifications in light of violation traces observed within the operational environment. Controller synthesis can then automatically generate implementations that are guaranteed to satisfy these specifications in every environment.
Specification learning is implemented using general-purpose AI systems. These systems are highly configurable, and the configuration choice heavily affects the effectiveness. Setting configuration parameters is far from obvious as they bear no clear semantic relation with the adaptation task. State of the art requires configurations to be set by domain experts at design time for each application domain.
In this paper, we argue that to create assured control systems that can effectively and efficiently adapt at runtime, the learning systems upon which they are built must also have adaptive learning strategies for determining configurations at runtime. We demonstrate this idea with a proof-of-concept that computes domain-dependent policies using reinforcement learning.
Thu 18 NovDisplayed time zone: Hobart change
18:00 - 19:00
|FirmGuide: Boosting the Capability of Rehosting Embedded Linux Kernels through Model-Guided Kernel Execution|
Qiang Liu Zhejiang University, Cen Zhang Nanyang Technological University, Lin Ma Zhejiang University, Muhui Jiang The Hong Kong Polytechnic University; Zhejiang University, Yajin Zhou Zhejiang University, Lei Wu Zhejiang University, Wenbo Shen Zhejing University, Xiapu Luo Hong Kong Polytechnic University, Yang Liu Nanyang Technological University, Kui Ren Zhejiang UniversityPre-print
|iFIZZ: Deep-State and Efficient Fault-Scenario Generation to Test IoT Firmware|
Peiyu Liu Zhejiang University, Shouling Ji Zhejiang University, Xuhong Zhang Zhejiang University, Qinming Dai Zhejiang University, Kangjie Lu University of Minnesota, Lirong Fu Zhejiang University, Wenzhi Chen Zhejiang University, Peng Cheng Zhejiang University, Wenhai Wang Zhejiang University, Raheem Beyah Georgia Institute of Technology
|BIFF: Practical Binary Fuzzing Framework for Programs of IoT and Mobile Devices|
Cen Zhang Nanyang Technological University, Yuekang Li Nanyang Technological University, Hongxu Chen Nanyang Technological University, Xiaoxing Luo Huawei Technologies Co., Ltd., Miaohua Li Huawei Technologies Co., Ltd., Anh Quynh Nguyen Nanyang Technological University, Yang Liu Nanyang Technological University
|Adaptation 2.0: Adapting Specification Learners in Assured Adaptive Systems|