Related papers: TorchLean: Formalizing Neural Networks in Lean

We propose Trusted Neural Network (TNN) models, which are deep neural network models that satisfy safety constraints critical to the application domain. We investigate different mechanisms for incorporating rule-based knowledge in the form…

Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication). While many impressive static verification…

Neural decompilers are machine learning models that reconstruct the source code from an executable program. Critical to the lifecycle of any machine learning model is an evaluation of its effectiveness. However, existing techniques for…

The physics community relies on index notation to effectively manipulate types of tensors. This paper introduces the first formally verified implementation of index notation in the interactive theorem prover Lean 4. By integrating index…

Unlike human-engineered systems such as aeroplanes, where each component's role and dependencies are well understood, the inner workings of AI models remain largely opaque, hindering verifiability and undermining trust. This paper…

We investigate two questions in this paper: First, we ask to what extent "MPC friendly" models are already supported by major Machine Learning frameworks such as TensorFlow or PyTorch. Prior works provide protocols that only work on…

The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important…

Our goal is a modern approach to answering questions via systematic reasoning where answers are supported by human interpretable proof trees grounded in an NL corpus of authoritative facts. Such a system would help alleviate the challenges…

Proving mathematical theorems using computer-verifiable formal languages like Lean significantly impacts mathematical reasoning. One approach to formal theorem proving involves generating complete proofs using Large Language Models (LLMs)…

In the field of machine unlearning, certified unlearning has been extensively studied in convex machine learning models due to its high efficiency and strong theoretical guarantees. However, its application to deep neural networks (DNNs),…

The growing reliance on artificial intelligence in safety- and security-critical applications is raising concerns about the robustness of neural networks to erroneous or adversarial input. Certification is a methodology for ensuring model…

Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that leverages the capabilities of language models to interpret the…

Clinicians are often very sceptical about applying automatic image processing approaches, especially deep learning based methods, in practice. One main reason for this is the black-box nature of these approaches and the inherent problem of…

Recent progress in vision-language models (VLMs) has opened new possibilities for robot task planning, but these models often produce incorrect action sequences. To address these limitations, we propose VeriGraph, a novel framework that…

Despite deep learning models running well-defined mathematical functions, we lack a formal mathematical framework for describing model architectures. Ad-hoc notation, diagrams, and pseudocode poorly handle nonlinear broadcasting and the…

Graph neural networks are becoming increasingly popular in the field of machine learning due to their unique ability to process data structured in graphs. They have also been applied in safety-critical environments where perturbations…

Most methods for neural network verification focus on bounding the image, i.e., set of outputs for a given input set. This can be used to, for example, check the robustness of neural network predictions to bounded perturbations of an input.…

We consider efficiency in the implementation of deep neural networks. Hardware accelerators are gaining interest as machine learning becomes one of the drivers of high-performance computing. In these accelerators, the directed graph…

Deep neural networks (DNNs) are widely used in real-world applications, yet they remain vulnerable to errors and adversarial attacks. Formal verification offers a systematic approach to identify and mitigate these vulnerabilities, enhancing…

Seeking effective neural networks is a critical and practical field in deep learning. Besides designing the depth, type of convolution, normalization, and nonlinearities, the topological connectivity of neural networks is also important.…