English
Related papers

Related papers: Reductions in local certification

200 papers

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

Certificates to a linear algebra computation are additional data structures for each output, which can be used by a---possibly randomized---verification algorithm that proves the correctness of each output. The certificates are essentially…

Symbolic Computation · Computer Science 2020-01-09 Jean-Guillaume Dumas , Erich Kaltofen

As state-of-the-art neural networks are deployed on reasoning and algorithmic tasks, exactness guarantees become increasingly important. However, high average-case accuracy can still mask inconsistent behaviors. This motivates exact…

Machine Learning · Computer Science 2026-05-25 Artur Back de Luca , Kimon Fountoulakis

Model checking large networks of processes is challenging due to state explosion. In many cases, individual processes are isomorphic, but there is insufficient global symmetry to simplify model checking. This work considers the verification…

Logic in Computer Science · Computer Science 2019-03-26 Kedar S. Namjoshi , Richard J. Trefler

Certifiable local robustness, which rigorously precludes small-norm adversarial examples, has received significant attention as a means of addressing security concerns in deep learning. However, for some classification problems, local…

Machine Learning · Computer Science 2021-06-15 Klas Leino , Matt Fredrikson

A vertex $v\in V(G)$ is said to distinguish two vertices $x,y\in V(G)$ of a nontrivial connected graph $G$ if the distance from $v$ to $x$ is different from the distance from $v$ to $y$. A set $S\subset V(G)$ is a local metric generator for…

Combinatorics · Mathematics 2015-05-25 Gabriel A. Barragan-Ramirez , Juan A. Rodriguez-Velazquez

Internal positivity offers a computationally cheap certificate for external (input-output) positivity of a linear time-invariant system. However, the drawback with this certificate lies in its realization dependency. Firstly, computing such…

Optimization and Control · Mathematics 2022-02-17 Christian Grussler , Anders Rantzer

Distributionally Robust (DR) optimization aims to certify worst-case risk within a Wasserstein uncertainty set. Current certifications typically rely either on global Lipschitz bounds, which are often conservative, or on local gradient…

Optimization and Control · Mathematics 2026-04-09 Hong T. M. Chu

Certifying the robustness of a graph-based machine learning model poses a critical challenge for safety. Current robustness certificates for graph classifiers guarantee output invariance with respect to the total number of node pair flips…

Machine Learning · Computer Science 2023-06-27 Pierre Osselin , Henry Kenlay , Xiaowen Dong

Recent work has exposed the vulnerability of computer vision models to vector field attacks. Due to the widespread usage of such models in safety-critical applications, it is crucial to quantify their robustness against such spatial…

Machine Learning · Computer Science 2021-02-02 Anian Ruoss , Maximilian Baader , Mislav Balunović , Martin Vechev

We extend classical methods of computational complexity to the realm of distributed computing, where they sometimes prove more effective than in their original context. Our focus is on decision problems in the LOCAL model, a setting in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-08 Fabian Reiter

We discuss optimization problems over convex cones in which membership is difficult to verify directly. In the standard theory of duality, vectors in the dual cone $K^*$ are associated with separating hyperplanes and interpreted as…

Optimization and Control · Mathematics 2026-03-27 Joonyeob Lee , Dávid Papp , Anita Varga

We introduce a low-memory framework for certifying numerical solutions to polynomial systems which uses solution iterators and spatial partitioning trees to reduce memory requirements. We provide a prototypical algorithm, analyze its…

Numerical Analysis · Mathematics 2026-04-21 Paul Breiding , Taylor Brysiewicz , David K. Johnson

Property graphs can be used to represent heterogeneous networks with labeled (attributed) vertices and edges. Given a property graph, simulating another graph with same or greater size with the same statistical properties with respect to…

Social and Information Networks · Computer Science 2019-07-18 Arun V. Sathanur , Sutanay Choudhury , Cliff Joslyn , Sumit Purohit

Inspired by branch-and-bound and cutting plane proofs in mixed-integer optimization and proof complexity, we develop a general approach via Hoffman's Helly systems. This helps to distill the main ideas behind optimality and infeasibility…

Optimization and Control · Mathematics 2022-06-29 Amitabh Basu , Tongtong Chen , Michele Conforti , Hongyi Jiang

We present a novel approach to non-convex optimization with certificates, which handles smooth functions on the hypercube or on the torus. Unlike traditional methods that rely on algebraic properties, our algorithm exploits the regularity…

Optimization and Control · Mathematics 2023-12-21 Gaspard Beugnot , Julien Mairal , Alessandro Rudi

Despite the exploding interest in graph neural networks there has been little effort to verify and improve their robustness. This is even more alarming given recent findings showing that they are extremely vulnerable to adversarial attacks…

Machine Learning · Computer Science 2019-12-20 Aleksandar Bojchevski , Stephan Günnemann

In this paper, we study the problem of certifying whether a graph is bipartite (i.e. $2$-colorable) with a locally checkable proof (LCP) that is able to hide a $2$-coloring from the verifier. More precisely, we say an LCP for $2$-coloring…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-26 Benjamin Jauregui , Augusto Modanese , Pedro Montealegre , Martín Ríos-Wilson

We propose and investigate probabilistic guarantees for the adversarial robustness of classification algorithms. While traditional formal verification approaches for robustness are intractable and sampling-based approaches do not provide…

Machine Learning · Computer Science 2025-11-11 Peter Blohm , Patrick Indri , Thomas Gärtner , Sagar Malhotra

In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications can compromise the…

Machine Learning · Computer Science 2024-06-13 Andrew C. Cullen , Shijie Liu , Paul Montague , Sarah M. Erfani , Benjamin I. P. Rubinstein