The deployment of Artificial Neural Networks (ANNs) in safety-critical applications poses a number of new verification and certification challenges. In particular, for ANN-enabled self-driving vehicles it is important to establish properties about the resilience of ANNs to noisy or even maliciously manipulated sensory input. We are addressing these challenges by defining resilience properties of ANN-based classifiers as the maximum amount of input or sensor perturbation which is still tolerated. This problem of computing maximum perturbation bounds for ANNs is then reduced to solving mixed integer optimization problems (MIP). A number of MIP encoding heuristics are developed for drastically reducing MIP-solver runtimes, and using parallelization of MIP-solvers results in an almost linear speed-up in the number (up to a certain limit) of computing cores in our experiments. We demonstrate the effectiveness and scalability of our approach by means of computing maximum resilience bounds for a number of ANN benchmark sets ranging from typical image recognition scenarios to the autonomous maneuvering of robots.

For using neural networks in safety critical domains, it is important to know if a decision made by a neural network is supported by prior similarities in training. We propose runtime neuron activation pattern monitoring -after the standard training process, one creates a monitor by feeding the training data to the network again in order to store the neuron activation patterns in abstract form. In operation, a classification decision over an input is further supplemented by examining if a pattern similar (measured by Hamming distance) to the generated pattern is contained in the monitor. If the monitor does not contain any pattern similar to the generated pattern, it raises a warning that the decision is not based on the training data. Our experiments show that, by adjusting the similarity-threshold for activation patterns, the monitors can report a significant portion of misclassfications to be not supported by training with a small false-positive rate, when evaluated on a test set.

We study the problem of formal verification of Binarized Neural Networks (BNN), which have recently been proposed as a energyefficient alternative to traditional learning networks. The verification of BNNs, using the reduction to hardware verification, can be even more scalable by factoring computations among neurons within the same layer. By proving the NP-hardness of finding optimal factoring as well as the hardness of PTAS approximability, we design polynomial-time search heuristics to generate factoring solutions. The overall framework allows applying verification techniques to moderately-sized BNNs for embedded devices with thousands of neurons and inputs.

Systematically testing models learned from neural networks remains a crucial unsolved barrier to successfully justify safety for autonomous vehicles engineered using data-driven approach. We propose quantitative k-projection coverage as a metric to mediate combinatorial explosion while guiding the data sampling process. By assuming that domain experts propose largely independent environment conditions and by associating elements in each condition with weights, the product of these conditions forms scenarios, and one may interpret weights associated with each equivalence class as relative importance. Achieving full k-projection coverage requires that the data set, when being projected to the hyperplane formed by arbitrarily selected k-conditions, covers each class with number of data points no less than the associated weight. For the general case where scenario composition is constrained by rules, precisely computing k-projection coverage remains in NP. In terms of finding minimum test cases to achieve full coverage, we present theoretical complexity for important sub-cases and an encoding to 0-1 integer programming. We have implemented a research prototype that generates test cases for a visual object detection unit in automated driving, demonstrating the technological feasibility of our proposed coverage criterion. IBM CPLEX OptimizationStudio: https

Early stages of system development involve outlining desired features such as functionality, availability, or usability. Specifications are derived from these features that concretize vague ideas presented in natural languages. The challenge for the verification and validation of specifications arises from the syntax and semantic gap between different representations and the need of automatic tools. In this paper, we present a requirementconsistency maintenance framework to produce consistent representations. The first part is the automatic translation from natural languages describing functionalities to formal logic with an abstraction of time. It extends pure syntactic parsing by adding semantic reasoning and the support of partitioning input and output variables. The second part is the use of synthesis techniques to examine if the requirements are consistent in terms of realizability. When the process fails, the formulas that cause the inconsistency are reported to locate the problem.