English
Related papers

Related papers: Achieving Domain-Independent Certified Robustness …

200 papers

We consider a neural network architecture designed to solve inverse problems where the degradation operator is linear and known. This architecture is constructed by unrolling a forward-backward algorithm derived from the minimization of an…

Optimization and Control · Mathematics 2025-10-02 Emilie Chouzenoux , Cecile Della Valle , Jean-Christophe Pesquet

Patch robustness certification ensures no patch within a given bound on a sample can manipulate a deep learning model to predict a different label. However, existing techniques cannot certify samples that cannot meet their strict bars at…

Machine Learning · Computer Science 2023-09-08 Qilin Zhou , Zhengyuan Wei , Haipeng Wang , W. K. Chan

This paper is concerned with the training of neural networks (NNs) under semidefinite constraints, which allows for NN training with robustness and stability guarantees. In particular, we focus on Lipschitz bounds for NNs. Exploiting the…

Machine Learning · Computer Science 2022-09-21 Patricia Pauli , Niklas Funcke , Dennis Gramlich , Mohamed Amine Msalmi , Frank Allgöwer

With the rise of deep neural networks, the challenge of explaining the predictions of these networks has become increasingly recognized. While many methods for explaining the decisions of deep neural networks exist, there is currently no…

Machine Learning · Computer Science 2022-07-13 Ian E. Nielsen , Dimah Dera , Ghulam Rasool , Nidhal Bouaynaya , Ravi P. Ramachandran

Formal explainability guarantees the rigor of computed explanations, and so it is paramount in domains where rigor is critical, including those deemed high-risk. Unfortunately, since its inception formal explainability has been hampered by…

Artificial Intelligence · Computer Science 2024-12-04 Xuanxiang Huang , Joao Marques-Silva

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

While neural networks can enjoy an outstanding flexibility and exhibit unprecedented performance, the mechanism behind their behavior is still not well-understood. To tackle this fundamental challenge, researchers have tried to restrict and…

Machine Learning · Computer Science 2024-12-17 Yuri Kinoshita , Taro Toyoizumi

Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers…

Machine Learning · Computer Science 2020-10-23 Moran Shkolnik , Brian Chmiel , Ron Banner , Gil Shomron , Yury Nahshan , Alex Bronstein , Uri Weiser

Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Although numerous state-of-the-art certified training methods…

Machine Learning · Computer Science 2022-10-27 Pratik Vaishnavi , Kevin Eykholt , Amir Rahmati

Text classifiers suffer from small perturbations, that if chosen adversarially, can dramatically change the output of the model. Verification methods can provide robustness certificates against such adversarial perturbations, by computing a…

Machine Learning · Computer Science 2025-02-21 Elias Abad Rocamora , Grigorios G. Chrysos , Volkan Cevher

The highly non-linear nature of deep neural networks causes them to be susceptible to adversarial examples and have unstable gradients which hinders interpretability. However, existing methods to solve these issues, such as adversarial…

Machine Learning · Computer Science 2023-01-11 Suraj Srinivas , Kyle Matoba , Himabindu Lakkaraju , Francois Fleuret

Learning representations that capture the underlying data generating process is a key problem for data efficient and robust use of neural networks. One key property for robustness which the learned representation should capture and which…

Machine Learning · Computer Science 2022-06-24 Mathieu Chevalley , Charlotte Bunne , Andreas Krause , Stefan Bauer

Performative prediction is a framework for learning models that influence the data they intend to predict. We focus on finding classifiers that are performatively stable, i.e. optimal for the data distribution they induce. Standard…

Machine Learning · Computer Science 2025-02-07 Mehrnaz Mofakhami , Ioannis Mitliagkas , Gauthier Gidel

Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery and certified detection. They aim to label malicious…

Software Engineering · Computer Science 2024-05-14 Qilin Zhou , Zhengyuan Wei , Haipeng Wang , Bo Jiang , W. K. Chan

Recent progress in Neural Causal Models (NCMs) showcased how identification and partial identification of causal effects can be automatically carried out via training of neural generative models that respect the constraints encoded in a…

Machine Learning · Computer Science 2025-06-17 Jiyuan Tan , Jose Blanchet , Vasilis Syrgkanis

In recent years, substantial advancements have been made in the development of large language models, achieving remarkable performance across diverse tasks. To evaluate the knowledge ability of language models, previous studies have…

Computation and Language · Computer Science 2024-05-30 Xunjian Yin , Xu Zhang , Jie Ruan , Xiaojun Wan

CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme Value Theory (EVT) based robustness score for large-scale deep neural networks (DNNs). In this paper, we propose two extensions on this robustness score. First, we…

Machine Learning · Computer Science 2018-10-23 Tsui-Wei Weng , Huan Zhang , Pin-Yu Chen , Aurelie Lozano , Cho-Jui Hsieh , Luca Daniel

The monotonic dependence of the outputs of a neural network on some of its inputs is a crucial inductive bias in many scenarios where domain knowledge dictates such behavior. This is especially important for interpretability and fairness…

Machine Learning · Computer Science 2023-07-17 Ouail Kitouni , Niklas Nolte , Michael Williams

Existing techniques for certifying the robustness of models for discrete data either work only for a small class of models or are general at the expense of efficiency or tightness. Moreover, they do not account for sparsity in the input…

Machine Learning · Computer Science 2023-02-28 Aleksandar Bojchevski , Johannes Gasteiger , Stephan Günnemann

In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does not overcome the…

Machine Learning · Computer Science 2019-09-13 Chris Finlay , Jeff Calder , Bilal Abbasi , Adam Oberman