Related papers: Scalable Surrogate Verification of Image-based Neu…

Regular model checking is a technique for the verification of infinite-state systems whose configurations can be represented as finite words over a suitable alphabet. The form we are studying applies to systems whose set of initial…

Perception-based neural network controllers are increasingly used in autonomous systems that rely on visual inputs to operate in the real world. Ensuring the safety of such systems under uncertainty is challenging. Existing verification…

We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of stochastic simulators. Unlike traditional approaches to surrogate modeling, our surrogates retain the interpretable structure and…

A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs),…

The arising application of neural networks (NN) in robotic systems has driven the development of safety verification methods for neural network dynamical systems (NNDS). Recursive techniques for reachability analysis of dynamical systems in…

Recent advances in Generative Artificial Intelligence have fueled numerous applications, particularly those involving Generative Adversarial Networks (GANs), which are essential for synthesizing realistic photos and videos. However,…

Medical image synthesis is a challenging task due to the scarcity of paired data. Several methods have applied CycleGAN to leverage unpaired data, but they often generate inaccurate mappings that shift the anatomy. This problem is further…

Providing safety guarantees for autonomous systems is difficult as these systems operate in complex environments that require the use of learning-enabled components, such as deep neural networks (DNNs) for visual perception. DNNs are hard…

Machine learning driven image-based controllers allow robotic systems to take intelligent actions based on the visual feedback from their environment. Understanding when these controllers might lead to system safety violations is important…

This paper studies the security of cyber-physical systems under attacks. Our goal is to design system parameters, such as a set of initial conditions and input bounds so that it is secure by design. To this end, we propose new sufficient…

Neural networks are increasingly deployed in real-world safety-critical domains such as autonomous driving, aircraft collision avoidance, and malware detection. However, these networks have been shown to often mispredict on inputs with…

In this paper, we consider the problem of formally verifying a Neural Network (NN) based autonomous landing system. In such a system, a NN controller processes images from a camera to guide the aircraft while approaching the runway. A…

Most work on the formal verification of neural networks has focused on bounding the set of outputs that correspond to a given set of inputs (for example, bounded perturbations of a nominal input). However, many use cases of neural network…

Neural networks serve as effective controllers in a variety of complex settings due to their ability to represent expressive policies. The complex nature of neural networks, however, makes their output difficult to verify and predict, which…

Weakly-supervised learning has become a popular technology in recent years. In this paper, we propose a novel medical image classification algorithm, called Weakly-Supervised Generative Adversarial Networks (WSGAN), which only uses a small…

We present a practical verification method for safety analysis of the autonomous driving system (ADS). The main idea is to build a surrogate model that quantitatively depicts the behaviour of an ADS in the specified traffic scenario. The…

Modern autonomous vehicle systems use complex perception and control components. These components can rapidly change during development of such systems, requiring constant re-testing. Unfortunately, high-fidelity simulations of these…

We propose a methodology for falsifying safety properties in robotic vehicle systems through property-guided reduction and surrogate execution. By isolating only the control logic and physical dynamics relevant to a given specification, we…

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…

The cycleGAN is becoming an influential method in medical image synthesis. However, due to a lack of direct constraints between input and synthetic images, the cycleGAN cannot guarantee structural consistency between these two images, and…