Related papers: A Certified Proof Checker for Deep Neural Network …

With the rapid growth of machine learning, deep neural networks (DNNs) are now being used in numerous domains. Unfortunately, DNNs are "black-boxes", and cannot be interpreted by humans, which is a substantial concern in safety-critical…

Formal verification of complex algorithms is challenging. Verifying their implementations goes beyond the state of the art of current automatic verification tools and usually involves intricate mathematical theorems. Certifying algorithms…

Over the past few years, deep neural networks (DNNs) have been continuously expanding their real-world applications for source code processing tasks across the software engineering domain, e.g., clone detection, code search, comment…

Machine Learning (ML) is increasingly used to implement advanced applications with non-deterministic behavior, which operate on the cloud-edge continuum. The pervasive adoption of ML is urgently calling for assurance solutions assessing…

The testing of Deep Neural Networks (DNNs) has become increasingly important as DNNs are widely adopted by safety critical systems. While many test adequacy criteria have been suggested, automated test input generation for many types of…

For typical first-order logical theories, satisfying assignments have a straightforward finite representation that can directly serve as a certificate that a given assignment satisfies the given formula. For non-linear real arithmetic…

Deep neural networks (DNNs), such as the widely-used GPT-3 with billions of parameters, are often kept secret due to high training costs and privacy concerns surrounding the data used to train them. Previous approaches to securing DNNs…

One major drawback of deep convolutional neural networks (CNNs) for use in safety critical applications is their black-box nature. This makes it hard to verify or monitor complex, symbolic requirements on already trained computer vision…

The great economic values of deep neural networks (DNNs) urge AI enterprises to protect their intellectual property (IP) for these models. Recently, proof-of-training (PoT) has been proposed as a promising solution to DNN IP protection,…

Correctness of results from mixed-integer linear programming (MILP) solvers is critical, particularly in the context of applications such as hardware verification, compiler optimization, or machine-assisted theorem proving. To this end,…

Trained Deep Neural Network (DNN) models are considered valuable Intellectual Properties (IP) in several business models. Prevention of IP theft and unauthorized usage of such DNN models has been raised as of significant concern by…

Deep Neural Networks (DNNs), as valuable intellectual property, face unauthorized use. Existing protections, such as digital watermarking, are largely passive; they provide only post-hoc ownership verification and cannot actively prevent…

Formal verification using interactive theorem provers ensures high-quality software. However, writing proof scripts for interactive theorem provers is labor-intensive and requires deep expertise. Recent studies have leveraged deep learning…

We present new algorithms for a posteriori verification of neural networks (NNs) approximating solutions to PDEs. These verification algorithms compute accurate estimates of $L^p$ norms of NNs and their derivatives. When combined with…

Deep neural networks (DNNs) have recently achieved impressive success across a wide range of real-world vision and language processing tasks, spanning from image classification to many other downstream vision tasks, such as object…

Contemporary DNN testing works are frequently conducted using metamorphic testing (MT). In general, de facto MT frameworks mutate DNN input images using semantics-preserving mutations and determine if DNNs can yield consistent predictions.…

Deep Neural Networks (DNNs) and their accelerators are being deployed ever more frequently in safety-critical applications leading to increasing reliability concerns. A traditional and accurate method for assessing DNNs' reliability has…

We introduce a machine learning approach to model checking temporal logic, with application to formal hardware verification. Model checking answers the question of whether every execution of a given system satisfies a desired temporal logic…

Machine learning models are highly vulnerable to label flipping, i.e., the adversarial modification (poisoning) of training labels to compromise performance. Thus, deriving robustness certificates is important to guarantee that test…

Recent advances in Deep Machine Learning have shown promise in solving complex perception and control loops via methods such as reinforcement and imitation learning. However, guaranteeing safety for such learned deep policies has been a…