English
Related papers

Related papers: Getting a-Round Guarantees: Floating-Point Attacks…

200 papers

The ability of machine learning (ML) classification models to resist small, targeted input perturbations -- known as adversarial attacks -- is a key measure of their safety and reliability. We show that floating-point non-associativity…

Machine Learning · Computer Science 2025-08-25 Sanjif Shanmugavelu , Mathieu Taillefumier , Christopher Culver , Vijay Ganesh , Oscar Hernandez , Ada Sedova

Roundoff errors cannot be avoided when implementing numerical programs with finite precision. The ability to reason about rounding is especially important if one wants to explore a range of potential representations, for instance for FPGAs…

Numerical Analysis · Computer Science 2016-11-28 Victor Magron , George Constantinides , Alastair Donaldson

Neural networks are successful in various applications but are also susceptible to adversarial attacks. To show the safety of network classifiers, many verifiers have been introduced to reason about the local robustness of a given input to…

Machine Learning · Computer Science 2024-03-07 Anan Kabaha , Dana Drachsler-Cohen

As machine learning (ML) systems become pervasive, safeguarding their security is critical. However, recently it has been demonstrated that motivated adversaries are able to mislead ML systems by perturbing test data using semantic…

Machine Learning · Computer Science 2021-11-17 Linyi Li , Maurice Weber , Xiaojun Xu , Luka Rimanic , Bhavya Kailkhura , Tao Xie , Ce Zhang , Bo Li

Implicit neural networks are a general class of learning models that replace the layers in traditional feedforward models with implicit algebraic equations. Compared to traditional learning models, implicit networks offer competitive…

Machine Learning · Computer Science 2021-12-13 Saber Jafarpour , Matthew Abate , Alexander Davydov , Francesco Bullo , Samuel Coogan

Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that…

Machine Learning · Computer Science 2018-12-04 Shiqi Wang , Yizheng Chen , Ahmed Abdou , Suman Jana

Randomized smoothing has emerged as a potent certifiable defense against adversarial attacks by employing smoothing noises from specific distributions to ensure the robustness of a smoothed classifier. However, the utilization of Monte…

Machine Learning · Computer Science 2025-04-01 Devansh Bhardwaj , Kshitiz Kaushik , Sarthak Gupta

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

Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks. Recent studies have introduced "smoothed policies" in order to enhance its robustness. Yet, it is still…

Machine Learning · Computer Science 2023-12-13 Ronghui Mu , Leandro Soriano Marcolino , Tianle Zhang , Yanghao Zhang , Xiaowei Huang , Wenjie Ruan

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

The literature on provable robustness in machine learning has primarily focused on static prediction problems, such as image classification, in which input samples are assumed to be independent and model performance is measured as an…

Machine Learning · Computer Science 2023-03-30 Aounon Kumar , Vinu Sankar Sadasivan , Soheil Feizi

Existing certified training methods can only train models to be robust against a certain perturbation type (e.g. $l_\infty$ or $l_2$). However, an $l_\infty$ certifiably robust model may not be certifiably robust against $l_2$ perturbation…

Machine Learning · Computer Science 2026-04-15 Enyi Jiang , David S. Cheung , Gagandeep Singh

Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region. But, currently, this robustness comes at a cost of degraded standard accuracies and slower inference times. We…

Computer Vision and Pattern Recognition · Computer Science 2021-10-18 Hadi Salman , Saachi Jain , Eric Wong , Aleksander Mądry

Quantization, a commonly used technique to reduce the memory footprint of a neural network for edge computing, entails reducing the precision of the floating-point representation used for the parameters of the network. The impact of such…

Machine Learning · Computer Science 2019-03-27 Abhishek Murthy , Himel Das , Md Ariful Islam

The growing penetration of renewable and distributed generation is transforming power systems and challenging conventional protection schemes that rely on fixed settings and local measurements. Machine learning (ML) offers a data-driven…

Machine Learning · Computer Science 2025-12-18 Julian Oelhaf , Mehran Pashaei , Georg Kordowich , Christian Bergler , Andreas Maier , Johann Jäger , Siming Bayer

Studying the robustness of machine learning models is important to ensure consistent model behaviour across real-world settings. To this end, adversarial robustness is a standard framework, which views robustness of predictions through a…

Machine Learning · Computer Science 2024-07-09 Tessa Han , Suraj Srinivas , Himabindu Lakkaraju

Despite the growing prevalence of artificial neural networks in real-world applications, their vulnerability to adversarial attacks remains a significant concern, which motivates us to investigate the robustness of machine learning models.…

Machine Learning · Computer Science 2024-08-23 Jie Wang , Rui Gao , Yao Xie

Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new attacks over time. A natural solution is to adapt the defended…

Machine Learning · Computer Science 2025-02-07 Sihui Dai , Christian Cianfarani , Arjun Bhagoji , Vikash Sehwag , Prateek Mittal

We study the problem of certifying the robustness of Bayesian neural networks (BNNs) to adversarial input perturbations. Given a compact set of input points $T \subseteq \mathbb{R}^m$ and a set of output points $S \subseteq \mathbb{R}^n$,…

Machine Learning · Computer Science 2023-06-26 Matthew Wicker , Andrea Patane , Luca Laurenti , Marta Kwiatkowska

In the past two decades we have seen the popularity of neural networks increase in conjunction with their classification accuracy. Parallel to this, we have also witnessed how fragile the very same prediction models are: tiny perturbations…

Machine Learning · Computer Science 2022-01-25 Mark Beliaev , Payam Delgosha , Hamed Hassani , Ramtin Pedarsani