English
Related papers

Related papers: Towards Reliable Neural Specifications

200 papers

A key to deciphering the inner workings of neural networks is understanding what a model has learned. Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing…

Machine Learning · Computer Science 2022-06-23 Alex Bäuerle , Daniel Jönsson , Timo Ropinski

Most work on the formal verification of neural networks has focused on bounding the set of outputs that correspond to a given set of inputs (for example, bounded perturbations of a nominal input). However, many use cases of neural network…

Machine Learning · Computer Science 2024-03-19 Suhas Kotha , Christopher Brix , Zico Kolter , Krishnamurthy Dvijotham , Huan Zhang

Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search space over the input features. In this work, we take a first step towards scaling exact…

Machine Learning · Computer Science 2026-05-26 David Boetius , Shahaf Bassan , Guy Katz , Stefan Leue , Tobias Sutter

Recurrent Neural Networks (RNNs) are a class of machine learning algorithms used for applications with time-series and sequential data. Recently, there has been a strong interest in executing RNNs on embedded devices. However, difficulties…

Neural and Evolutionary Computing · Computer Science 2020-03-23 Nesma M. Rezk , Madhura Purnaprajna , Tomas Nordström , Zain Ul-Abdin

In this work, we assess the theoretical limitations of determining guaranteed stability and accuracy of neural networks in classification tasks. We consider classical distribution-agnostic framework and algorithms minimising empirical risks…

Neural networks are increasingly employed in safety-critical domains. This has prompted interest in verifying or certifying logically encoded properties of neural networks. Prior work has largely focused on checking existential properties,…

Cryptography and Security · Computer Science 2019-06-26 Teodora Baluta , Shiqi Shen , Shweta Shinde , Kuldeep S. Meel , Prateek Saxena

Neural networks are vulnerable to adversarial attacks, i.e., small input perturbations can significantly affect the outputs of a neural network. Therefore, to ensure safety of neural networks in safety-critical environments, the robustness…

Machine Learning · Computer Science 2025-08-06 Lukas Koller , Tobias Ladner , Matthias Althoff

The formal specification and verification of machine learning programs saw remarkable progress in less than a decade, leading to a profusion of tools. However, diversity may lead to fragmentation, resulting in tools that are difficult to…

Software Engineering · Computer Science 2026-01-21 Michele Alberti , François Bobot , Julien Girard-Satabin , Alban Grastien , Aymeric Varasse , Zakaria Chihani

Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings. Most certification methods in the literature are designed for adversarial or worst-case inputs, but researchers…

Machine Learning · Computer Science 2023-01-26 Brendon G. Anderson , Somayeh Sojoudi

Neural networks are one of the most investigated and widely used techniques in Machine Learning. In spite of their success, they still find limited application in safety- and security-related contexts, wherein assurance about networks'…

Artificial Intelligence · Computer Science 2018-05-28 Francesco Leofante , Nina Narodytska , Luca Pulina , Armando Tacchella

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…

Machine Learning · Computer Science 2024-05-09 Rudy Bunel , Krishnamurthy Dvijotham , M. Pawan Kumar , Alessandro De Palma , Robert Stanforth

While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the real world. These defenses also come at a cost to accuracy.…

Machine Learning · Computer Science 2019-12-05 Varun Chandrasekaran , Brian Tang , Nicolas Papernot , Kassem Fawaz , Somesh Jha , Xi Wu

Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings. Most certification methods in the literature are designed for adversarial input uncertainty, but researchers…

Machine Learning · Computer Science 2023-01-26 Brendon G. Anderson , Somayeh Sojoudi

We investigate the complexity of the reachability problem for (deep) neural networks: does it compute valid output given some valid input? It was recently claimed that the problem is NP-complete for general neural networks and…

Computational Complexity · Computer Science 2026-04-08 Marco Sälzer , Martin Lange

Neural network verifiers aim to provide formal guarantees on model behavior, but existing verification benchmarks are fundamentally limited by their lack of ground-truth labels. As a result, verifier evaluation relies on indirect…

Machine Learning · Computer Science 2026-05-19 David Troxell , Yulia Alexandr , Sofia Hunt , Stephanie Lei , Guido Montúfar

As deep neural networks (DNNs) are increasingly used in safety-critical applications, there is a growing concern for their reliability. Even highly trained, high-performant networks are not 100% accurate. However, it is very difficult to…

Neural and Evolutionary Computing · Computer Science 2024-07-30 Eduard Pinconschi , Divya Gopinath , Rui Abreu , Corina S. Pasareanu

Sustainable research on computational models of neuronal networks requires published models to be understandable, reproducible, and extendable. Missing details or ambiguities about mathematical concepts and assumptions, algorithmic…

Quantifying the robustness of neural networks or verifying their safety properties against input uncertainties or adversarial attacks have become an important research area in learning-enabled systems. Most results concentrate around the…

Systems and Control · Electrical Eng. & Systems 2019-10-11 Mahyar Fazlyab , Manfred Morari , George J. Pappas

Deep Neural Networks (DNNs) have emerged as a powerful mechanism and are being increasingly deployed in real-world safety-critical domains. Despite the widespread success, their complex architecture makes proving any formal guarantees about…

Machine Learning · Computer Science 2020-03-26 Saket Dingliwal , Divyansh Pareek , Jatin Arora

Machine learning techniques often lack formal correctness guarantees, evidenced by the widespread adversarial examples that plague most deep-learning applications. This lack of formal guarantees resulted in several research efforts that aim…

Machine Learning · Computer Science 2024-06-11 Anahita Baninajjar , Ahmed Rezine , Amir Aminifar