Related papers: Towards Repairing Neural Networks Correctly
Reinforcement learning often uses neural networks to solve complex control tasks. However, neural networks are sensitive to input perturbations, which makes their deployment in safety-critical environments challenging. This work lifts…
There is an emerging trend in applying deep learning methods to control complex nonlinear systems. This paper considers enhancing the runtime safety of nonlinear systems controlled by neural networks in the presence of disturbance and…
Deep Neural Networks are increasingly adopted in critical tasks that require a high level of safety, e.g., autonomous driving. While state-of-the-art verifiers can be employed to check whether a DNN is unsafe w.r.t. some given property…
Deep learning has transformed the way we think of software and what it can do. But deep neural networks are fragile and their behaviors are often surprising. In many settings, we need to provide formal guarantees on the safety, security,…
This paper describes a verification case study on an autonomous racing car with a neural network (NN) controller. Although several verification approaches have been proposed over the last year, they have only been evaluated on…
Neural network verification tools currently support only a narrow class of specifications, typically expressed as low-level constraints over raw inputs and outputs. This limitation significantly hinders their adoption and practical…
Recurrent neural network (RNN) is an effective neural network in solving very complex supervised and unsupervised tasks. There has been a significant improvement in RNN field such as natural language processing, speech processing, computer…
In sequential decision making, neural networks (NNs) are nowadays commonly used to represent and learn the agent's policy. This area of application has implied new software quality assessment challenges that traditional validation and…
We develop the first (to the best of our knowledge) provably correct neural networks for a precise computational task, with the proof of correctness generated by an automated verification algorithm without any human input. Prior work on…
Probabilistic verification problems of neural networks are concerned with formally analysing the output distribution of a neural network under a probability distribution of the inputs. Examples of probabilistic verification problems include…
The solution of linear inverse problems arising, for example, in signal and image processing is a challenging problem since the ill-conditioning amplifies, in the solution, the noise present in the data. Recently introduced algorithms based…
With the widespread deployment of deep neural networks (DNNs), ensuring the reliability of DNN-based systems is of great importance. Serious reliability issues such as system failures can be caused by numerical defects, one of the most…
Model-based reinforcement learning (RL) has emerged as a promising tool for developing controllers for real world systems (e.g., robotics, autonomous driving, etc.). However, real systems often have constraints imposed on their state space…
This paper aims to enhance the computational efficiency of safety verification of neural network control systems by developing a guaranteed neural network model reduction method. First, a concept of model reduction precision is proposed to…
Adaptivity in multi-function radar systems is rapidly increasing, especially when moving towards fully adaptive, cognitive radar systems. However, the large number of available system configurations makes the rigorous verification and…
Recently, there is growing concern that machine-learning models, which currently assist or even automate decision making, reproduce, and in the worst case reinforce, bias of the training data. The development of tools and techniques for…
Barrier certificates play an important role in verifying the safety of continuous-time systems, including autonomous driving, robotic manipulators and other critical applications. Recently, ReLU neural barrier certificates -- barrier…
We present a novel technique for online safety verification of autonomous systems, which performs reachability analysis efficiently for both bounded and unbounded horizons by employing neural barrier certificates. Our approach uses barrier…
With edge-AI finding an increasing number of real-world applications, especially in industry, the question of functionally safe applications using AI has begun to be asked. In this body of work, we explore the issue of achieving dependable…
As the potential for neural networks to augment our daily lives grows, ensuring their quality through effective testing, debugging, and maintenance is essential. This is especially the case as we acknowledge the prospects of negative…