Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userReachable Set Estimation for Neural Network Control Systems: A Simulation-Guided Approach
95
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
The vulnerability of artificial intelligence (AI) and machine learning (ML) against adversarial disturbances and attacks significantly restricts their applicability in safety-critical systems including cyber-physical systems (CPS) equipped with neural network components at various stages of sensing and control. This paper addresses the reachable set estimation and safety verification problems for dynamical systems embedded with neural network components serving as feedback controllers. The closed-loop system can be abstracted in the form of a continuous-time sampled-data system under the control of a neural network controller. First, a novel reachable set computation method in adaptation to simulations generated out of neural networks is developed. The reachability analysis of a class of feedforward neural networks called multilayer perceptrons (MLP) with general activation functions is performed in the framework of interval arithmetic. Then, in combination with reachability methods developed for various dynamical system classes modeled by ordinary differential equations, a recursive algorithm is developed for over-approximating the reachable set of the closed-loop system. The safety verification for neural network control systems can be performed by examining the emptiness of the intersection between the over-approximation of reachable sets and unsafe sets. The effectiveness of the proposed approach has been validated with evaluations on a robotic arm model and an adaptive cruise control system.
rate research
Read More
In this work, the reachable set estimation and safety verification problems for a class of piecewise linear systems equipped with neural network controllers are addressed. The neural network is considered to consist of Rectified Linear Unit (ReLU) activation functions. A layer-by-layer approach is developed for the output reachable set computation of ReLU neural networks. The computation is formulated in the form of a set of manipulations for a union of polytopes. Based on the output reachable set for neural network controllers, the output reachable set for a piecewise linear feedback control system can be estimated iteratively for a given finite-time interval. With the estimated output reachable set, the safety verification for piecewise linear systems with neural network controllers can be performed by checking the existence of intersections of unsafe regions and output reach set. A numerical example is presented to illustrate the effectiveness of our approach.
This paper proposes a specification-guided framework for control of nonlinear systems with linear temporal logic (LTL) specifications. In contrast with well-known abstraction-based methods, the proposed framework directly characterizes the winning set, i.e., the set of initial conditions from which a given LTL formula can be realized, over the continuous state space of the system via a monotonic operator. Following this characterization, an algorithm is proposed to practically approximate the operator via an adaptive interval subdivision scheme, which yields a finite-memory control strategy. We show that the proposed algorithm is sound for full LTL specifications, and robustly complete for specifications recognizable by deterministic Buchi automata (DBA), the latter in the sense that control strategies can be found whenever the given specification can be satisfied with additional bounded disturbances. Without having to compute and store the abstraction and the resulting product system with the DBA, the proposed method is more memory efficient, which is demonstrated by complexity analysis and performance tests. A pre-processing stage is also devised to reduce computational cost via a decomposition of the specification. We show that the proposed method can effectively solve real-world control problems such as jet engine compressor control and motion planning for manipulators and mobile robots.
In this paper a novel approach to co-design controller and attack detector for nonlinear cyber-physical systems affected by false data injection (FDI) attack is proposed. We augment the model predictive controller with an additional constraint requiring the future---in some steps ahead---trajectory of the system to remain in some time-invariant neighborhood of a properly designed reference trajectory. At any sampling time, we compare the real-time trajectory of the system with the designed reference trajectory, and construct a residual. The residual is then used in a nonparametric cumulative sum (CUSUM) anomaly detector to uncover FDI attacks on input and measurement channels. The effectiveness of the proposed approach is tested with a nonlinear model regarding level control of coupled tanks.
This paper considers a constrained discrete-time linear system subject to actuation attacks. The attacks are modelled as false data injections to the system, such that the total input (control input plus injection) satisfies hard input constraints. We establish a sufficient condition under which it is not possible to maintain the states of the system within a compact state constraint set for all possible realizations of the actuation attack. The developed condition is a simple function of the spectral radius of the system, the relative sizes of the input and state constraint sets, and the proportion of the input constraint set allowed to the attacker.
Digital instrumentation and control (I&C) upgrades are a vital research area for nuclear industry. Despite their performance benefits, deployment of digital I&C in nuclear power plants (NPPs) has been limited. Digital I&C systems exhibit complex failure modes including common cause failures (CCFs) which can be difficult to identify. This paper describes the development of a redundancy-guided application of the Systems-Theoretic Process Analysis (STPA) and Fault Tree Analysis (FTA) for the hazard analysis of digital I&C in advanced NPPs. The resulting Redundancy-guided System-theoretic Hazard Analysis (RESHA) is applied for the case study of a representative state-of-the-art digital reactor trip system. The analysis qualitatively and systematically identifies the most critical CCFs and other hazards of digital I&C systems. Ultimately, RESHA can help researchers make informed decisions for how, and to what degree, defensive measures such as redundancy, diversity, and defense-in-depth can be used to mitigate or eliminate the potential hazards of digital I&C systems.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
