Related papers: TorchLean: Formalizing Neural Networks in Lean

There are a plethora of applications that demand high throughput and low latency algorithms leveraging machine learning methods. This need for real time processing can be seen in industries ranging from developing neural network based…

Neural networks are often susceptible to minor perturbations in input that cause them to misclassify. A recent solution to this problem is the use of globally-robust neural networks, which employ a function to certify that the…

Formal models are essential to specifying large, complex computer systems and verifying their correctness, but are notoriously expensive to write and maintain. Recent advances in generative AI show promise in generating certain forms of…

Tensors are higher-order extensions of matrices. While matrix methods form the cornerstone of machine learning and data analysis, tensor methods have been gaining increasing traction. However, software support for tensor operations is not…

We argue that trustworthy AI agents, especially in high-stakes and policy-governed domains, should make execution conditional on certified traces rather than rely only on stronger generative models, output-level guardrails, or post-hoc…

TextGrad is a novel approach to text-based automatic differentiation that enables composite AI systems to perform optimization without explicit numerical equations. However, it currently lacks self-verification mechanisms that ensure…

Rectified Linear Unit (ReLU) networks are piecewise-linear (PWL), so universal linear safety properties can be reduced to reasoning about linear constraints. Modern verifiers rely on SMT(LRA) procedures or MILP encodings, but a safety claim…

Artificial Intelligence agents are required to learn from their surroundings and to reason about the knowledge that has been learned in order to make decisions. While state-of-the-art learning from data typically uses sub-symbolic…

The challenge of automatically determining the correctness of test executions is referred to as the test oracle problem and is one of the key remaining issues for automated testing. The goal in this paper is to solve the test oracle problem…

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…

Learning monotonic models with respect to a subset of the inputs is a desirable feature to effectively address the fairness, interpretability, and generalization issues in practice. Existing methods for learning monotonic neural networks…

Modern verification tools for deep neural networks (DNNs) increasingly rely on abstraction to scale to realistic architectures. In parallel, proof production is becoming a critical requirement for increasing the reliability of DNN…

The reproduction of hardware architectures from academic papers remains a significant challenge due to the lack of publicly available source code and the complexity of hardware description languages (HDLs). To this end, we propose…

Formal verification has emerged as a promising method to ensure the safety and reliability of neural networks. However, many relevant properties, such as fairness or global robustness, pertain to the entire input space. If one applies…

Neural networks currently dominate the machine learning community and they do so for good reasons. Their accuracy on complex tasks such as image classification is unrivaled at the moment and with recent improvements they are reasonably easy…

We present a PyTorch package that compiles neural networks and their weights from Turing machine descriptions, producing models that exactly simulate the specified machine without any training. Given a transition function and a set of…

Neural networks are increasingly used to support decision-making. To verify their reliability and adaptability, researchers and practitioners have proposed a variety of tools and methods for tasks such as NN code verification, refactoring,…

Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can later be exploited.…

In deep learning applications, robustness measures the ability of neural models that handle slight changes in input data, which could lead to potential safety hazards, especially in safety-critical applications. Pre-deployment assessment of…

Neural certificates have emerged as a powerful tool in cyber-physical systems control, providing witnesses of correctness. These certificates, such as barrier functions, often learned alongside control policies, once verified, serve as…