Search Results

Neural networks are increasingly used in safety-critical applications such as robotics and autonomous vehicles. However, the deployment of neural-network-controlled systems (NNCSs) raises significant safety concerns. Many recent advances overlook ...

The rapid advance of deep reinforcement learning techniques enables the oversight of safety-critical systems through the utilization of Deep Neural Networks (DNNs). This underscores the pressing need to promptly establish certified safety ...

Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their behaviors should undergo rigorous guarantees before deployment in ...

• To the best of our knowledge, this is the first work using topological properties of NNs to tackle the safety verification problems of neural networks.
• The proposed set-boundary based method controls the wrapping effect of existing ...

Neural networks are central to many emerging technologies, but verifying their correctness remains a major challenge. It is known that network outputs can be sensitive and fragile to even small input perturbations, thereby increasing the risk of ...

This paper reports on the industrial use of our formal-method based interlocking verification tool, called SafeCap, and on what we needed to change in SafeCap as a result of our experience in applying it to a large number of commercial signalling ...

In many automated motion planning systems, vehicles are tasked with tracking a reference path or trajectory that is safe by design. However, due to various uncertainties, real vehicles may deviate from such references, potentially leading to ...

Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their behaviors should undergo rigorous guarantees before deployment in ...

Traditionally, extensive vehicle testing is applied to assure the robustness and safety of automotive systems. This approach is highly challenged by increasing system complexity. Formal verification lends a powerful framework for model-based ...

Approximating the set of reachable states of a dynamical system is an algorithmic way to rigorously reason about its safety. Despite progress on efficient algorithms for affine dynamical systems, available algorithms still lack ...

Many complex domains would benefit from the services of Large-scale, Safety-verified, Always-on (LSA) robotic systems. However, existing large-scale solutions often forego the complex reasoning required for safety verification and prescient ...

We present $\mathsf{SceneChecker}$, a tool for verifying scenarios involving vehicles executing complex plans in large cluttered workspaces. $\mathsf{SceneChecker}$ converts the scenario verification problem to a standard hybrid system verification problem, and solves ...$\mathsf{}$$\mathsf{}$$\mathsf{}$$$

We provide a new approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier functions, ...

Self-driving cars over the last decade have achieved significant progress like driving millions of miles without any human intervention. However, behavioral safety in applying deep-neural-network-based (DNN based) systems for self-driving cars ...

We provide a novel approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier ...

We study the fine-grained complexity of Leader Contributor Reachability ($\mathsf{LCR}$) and Bounded-Stage Reachability ($\mathsf{BSR}$), two variants of the safety verification problem for shared memory concurrent programs. For both problems, the memory is a single ...$\mathsf{}$$\mathsf{}\mathsf{}$$\mathsf{}$$\mathtt{}$$\mathtt{}$$\mathtt{}$${\mathcal{}}^{}{\mathtt{}\mathtt{}\mathrm{}}^{\mathtt{}\mathtt{}}{\mathtt{}}^{\mathtt{}}$${\mathcal{}}^{}{\mathrm{}}^{\mathtt{}}$$\mathsf{}$$\mathsf{}\mathsf{}$$\mathsf{}$$\mathtt{}$$\mathtt{}$$\mathsf{}$$\mathtt{}$$\mathtt{}$$\mathtt{}$$\mathtt{}$$\mathtt{}$$\mathtt{}$$\mathtt{}$

We introduce SAW, a tool for safety analysis of weakly-hard systems, in which traditional hard timing constraints are relaxed to allow bounded deadline misses for improving design flexibility and runtime resiliency. Safety verification is a key ...

We describe a method for verifying the temporal property of persistence in non-linear hybrid systems. Given some system and an initial set of states, the method establishes that system trajectories always eventually evolve into some specified ...

Ethereum smart contracts are public, immutable and distributed and, as such, they are prone to vulnerabilities sourcing from programming mistakes of developers. This paper presents SAFEVM, a verification tool for Ethereum smart contracts that makes use ...

In recent years, finite realtime nonlinear hybrid systems(FRNHS) have been widely used in the fields of biology, chemical control, embedded systems, etc. Its safety verification becomes more and more important. Compared with traditional hybrid systems, ...

In this paper we address the safety analysis of chemical plants controlled by programmable logic controllers (PLCs). We consider a specification of the control program of the PLCs, extended with the specification of the dynamic plant behavior. The ...