English
Related papers

Related papers: Stress-Testing Neural Network Verifiers with Prova…

200 papers

Traditional methods for formal verification (FV) of deep neural networks (DNNs) are constrained by a binary encoding of safety properties, where a model is classified as either safe or unsafe (robust or not robust). This binary encoding…

Artificial Intelligence · Computer Science 2025-05-09 Luca Marzari , Isabella Mastroeni , Alessandro Farinelli

Deep learning has emerged as an effective approach for creating modern software systems, with neural networks often surpassing hand-crafted systems. Unfortunately, neural networks are known to suffer from various safety and security issues.…

Machine Learning · Computer Science 2021-01-19 Guy Amir , Haoze Wu , Clark Barrett , Guy Katz

Hundreds of defenses have been proposed to make deep neural networks robust against minimal (adversarial) input perturbations. However, only a handful of these defenses held up their claims because correctly evaluating robustness is…

Machine Learning · Computer Science 2022-06-29 Roland S. Zimmermann , Wieland Brendel , Florian Tramer , Nicholas Carlini

As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not just the functional correctness, but also the formal verifiability of generated code.…

Machine Learning · Computer Science 2026-05-22 Yifan Bai , Xiaoyang Liu , Zihao Mou , Guihong Wang , Jian Yu , Shuhan Xie , Yantao Li , Yangyu Zhang , Jingwei Liang , Tao Luo

Malware, or software designed with harmful intent, is an ever-evolving threat that can have drastic effects on both individuals and institutions. Neural network malware classification systems are key tools for combating these threats but…

Cryptography and Security · Computer Science 2024-04-09 Preston K. Robinette , Diego Manzanas Lopez , Serena Serbinowska , Kevin Leach , Taylor T. Johnson

Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, i.e., miniscule malicious changes to inputs may induce unintuitive outputs. One key approach to verify and mitigate such robustness issues is to falsify…

Cryptography and Security · Computer Science 2025-10-07 Raik Dankworth , Gesina Schwalbe

The rising popularity of neural networks (NNs) in recent years and their increasing prevalence in real-world applications have drawn attention to the importance of their verification. While verification is known to be computationally…

Artificial Intelligence · Computer Science 2022-07-15 Natalia Slusarz , Ekaterina Komendantskaya , Matthew L. Daggitt , Robert Stewart

Ensuring the safety and efficiency of AI systems is a central goal of modern research. Formal verification provides guarantees of neural network robustness, while early exits improve inference efficiency by enabling intermediate…

Machine Learning · Computer Science 2025-12-25 Yizhak Yisrael Elboher , Avraham Raviv , Amihay Elboher , Zhouxing Shi , Omri Azencot , Hillel Kugler , Guy Katz

Formal verification is the next frontier for ensuring the correctness of code generated by Large Language Models (LLMs). While methods that co-generate code and formal specifications in formal languages, like Dafny, can, in principle, prove…

Programming Languages · Computer Science 2026-04-21 Lingfei Zeng , Fengdi Che , Xuhan Huang , Fei Ye , Xu Xu , Binhang Yuan , Jie Fu

Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification techniques for verifying neural network properties. While…

Cryptography and Security · Computer Science 2022-05-10 Youcheng Sun , Muhammad Usman , Divya Gopinath , Corina S. Păsăreanu

Neural network verification is an active and rapidly maturing research area, with a growing ecosystem of solvers and tools. The VNN-LIB standard was introduced to support interoperability in this ecosystem, but Version~1.0 has several…

Machine Learning · Computer Science 2026-05-11 Ann Roy , Allen Antony , Andrea Gimelli , Matthew L. Daggitt

Barrier certificates play an important role in verifying the safety of continuous-time systems, including autonomous driving, robotic manipulators and other critical applications. Recently, ReLU neural barrier certificates -- barrier…

Systems and Control · Electrical Eng. & Systems 2025-11-14 Dejin Ren , Yiling Xue , Taoran Wu , Bai Xue

Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data augmentation to partially mitigate such…

Computation and Language · Computer Science 2019-12-23 Po-Sen Huang , Robert Stanforth , Johannes Welbl , Chris Dyer , Dani Yogatama , Sven Gowal , Krishnamurthy Dvijotham , Pushmeet Kohli

Performance of trained neural network (NN) models, in terms of testing accuracy, has improved remarkably over the past several years, especially with the advent of deep learning. However, even the most accurate NNs can be biased toward a…

Machine Learning · Computer Science 2023-03-14 Mahum Naseer , Bharath Srinivas Prabakaran , Osman Hasan , Muhammad Shafique

The verification problem for neural networks is verifying whether a neural network will suffer from adversarial samples, or approximating the maximal allowed scale of adversarial perturbation that can be endured. While most prior work…

Machine Learning · Computer Science 2018-11-16 Qinglong Wang , Kaixuan Zhang , Xue Liu , C. Lee Giles

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

Machine Learning · Computer Science 2023-09-06 Ruihan Zhang , Peixin Zhang , Jun Sun

As large language models become integral to high-stakes applications, ensuring their robustness and fairness is critical. Despite their success, large language models remain vulnerable to adversarial attacks, where small perturbations, such…

Artificial Intelligence · Computer Science 2026-02-02 Danqing Chen , Tobias Ladner , Ahmed Rayen Mhadhbi , Matthias Althoff

Having reliable specifications is an unavoidable challenge in achieving verifiable correctness, robustness, and interpretability of AI systems. Existing specifications for neural networks are in the paradigm of data as specification. That…

Machine Learning · Computer Science 2023-03-20 Chuqin Geng , Nham Le , Xiaojie Xu , Zhaoyue Wang , Arie Gurfinkel , Xujie Si

Neural Ordinary Differential Equations (NODEs) are a novel neural architecture, built around initial value problems with learned dynamics which are solved during inference. Thought to be inherently more robust against adversarial…

Machine Learning · Computer Science 2023-03-10 Mustafa Zeqiri , Mark Niklas Müller , Marc Fischer , Martin Vechev

A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systematic and efficient…

Machine Learning · Computer Science 2024-06-03 You Li , Guannan Zhao , Shuyu Kong , Yunqi He , Hai Zhou