English
Related papers

Related papers: A PAC-Bayes Analysis of Adversarial Robustness

200 papers

Bayesian methods, distributionally robust optimization methods, and regularization methods are three pillars of trustworthy machine learning combating distributional uncertainty, e.g., the uncertainty of an empirical distribution compared…

Machine Learning · Computer Science 2024-03-26 Shixiong Wang , Haowei Wang

With the successful application of deep learning models in many real-world tasks, the model robustness becomes more and more critical. Often, we evaluate the robustness of the deep models by attacking them with purposely generated…

Machine Learning · Computer Science 2020-12-21 Jinyin Chen , Zhen Wang , Haibin Zheng , Jun Xiao , Zhaoyan Ming

Despite its wide use and empirical successes, the theoretical understanding and study of the behaviour and performance of the variational autoencoder (VAE) have only emerged in the past few years. We contribute to this recent line of work…

Machine Learning · Computer Science 2022-02-24 Badr-Eddine Chérief-Abdellatif , Yuyang Shi , Arnaud Doucet , Benjamin Guedj

This paper generalizes an important result from the PAC-Bayesian literature for binary classification to the case of ensemble methods for structured outputs. We prove a generic version of the \Cbound, an upper bound over the risk of models…

Machine Learning · Statistics 2015-06-16 François Laviolette , Emilie Morvant , Liva Ralaivola , Jean-Francis Roy

Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. In this work we frame the…

Machine Learning · Computer Science 2020-01-22 Avishek Joey Bose , Andre Cianflone , William L. Hamilton

Linear Autoencoders (LAEs) have shown strong performance in state-of-the-art recommender systems. However, this success remains largely empirical, with limited theoretical understanding. In this paper, we investigate the generalizability --…

Machine Learning · Statistics 2025-12-16 Ruixin Guo , Ruoming Jin , Xinyu Li , Yang Zhou

Machine-learning models are known to be vulnerable to evasion attacks that perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where the true threat cannot be assessed accurately by existing…

Machine Learning · Computer Science 2024-03-12 Weiran Lin , Keane Lucas , Neo Eyal , Lujo Bauer , Michael K. Reiter , Mahmood Sharif

Equivariant networks capture the inductive bias about the symmetry of the learning task by building those symmetries into the model. In this paper, we study how equivariance relates to generalization error utilizing PAC Bayesian analysis…

Machine Learning · Computer Science 2022-10-25 Arash Behboodi , Gabriele Cesa , Taco Cohen

Standard Bayesian learning is known to have suboptimal generalization capabilities under misspecification and in the presence of outliers. PAC-Bayes theory demonstrates that the free energy criterion minimized by Bayesian learning is a…

Machine Learning · Computer Science 2023-04-25 Matteo Zecchin , Sangwoo Park , Osvaldo Simeone , Marios Kountouris , David Gesbert

Motivated by safety-critical applications, test-time attacks on classifiers via adversarial examples has recently received a great deal of attention. However, there is a general lack of understanding on why adversarial examples arise;…

Machine Learning · Statistics 2019-06-20 Yizhen Wang , Somesh Jha , Kamalika Chaudhuri

This work studies the threats of adversarial attack on multivariate probabilistic forecasting models and viable defense mechanisms. Our studies discover a new attack pattern that negatively impact the forecasting of a target time series via…

Machine Learning · Computer Science 2023-04-17 Linbo Liu , Youngsuk Park , Trong Nghia Hoang , Hilaf Hasson , Jun Huan

The aim of this paper is to generalize the PAC-Bayesian theorems proved by Catoni in the classification setting to more general problems of statistical inference. We show how to control the deviations of the risk of randomized estimators. A…

Machine Learning · Statistics 2009-01-09 Pierre Alquier

The PAC-Bayesian approach is a powerful set of techniques to derive non- asymptotic risk bounds for random estimators. The corresponding optimal distribution of estimators, usually called the Gibbs posterior, is unfortunately intractable.…

Machine Learning · Statistics 2015-06-16 Pierre Alquier , James Ridgway , Nicolas Chopin

This paper is focused on dimension-free PAC-Bayesian bounds, under weak polynomial moment assumptions, allowing for heavy tailed sample distributions. It covers the estimation of the mean of a vector or a matrix, with applications to least…

Statistics Theory · Mathematics 2018-01-03 Olivier Catoni , Ilaria Giulini

We propose a general approach to evaluating the performance of robust estimators based on adversarial losses under misspecified models. We first show that adversarial risk is equivalent to the risk induced by a distributional adversarial…

Machine Learning · Statistics 2023-09-06 Changyu Liu , Yuling Jiao , Junhui Wang , Jian Huang

Prior literature on adversarial attack methods has mainly focused on attacking with and defending against a single threat model, e.g., perturbations bounded in Lp ball. However, multiple threat models can be combined into composite…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Lei Hsiung , Yun-Yun Tsai , Pin-Yu Chen , Tsung-Yi Ho

Adversarial robustness is a critical property in a variety of modern machine learning applications. While it has been the subject of several recent theoretical studies, many important questions related to adversarial robustness are still…

Machine Learning · Computer Science 2023-08-30 Pranjal Awasthi , Natalie S. Frank , Mehryar Mohri

PAC-Bayes learning is an established framework to both assess the generalisation ability of learning algorithms, and design new learning algorithm by exploiting generalisation bounds as training objectives. Most of the exisiting bounds…

Machine Learning · Statistics 2023-05-31 Maxime Haddouche , Benjamin Guedj

The field of defense strategies against adversarial attacks has significantly grown over the last years, but progress is hampered as the evaluation of adversarial defenses is often insufficient and thus gives a wrong impression of…

Machine Learning · Computer Science 2020-08-06 Francesco Croce , Matthias Hein

This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-case inputs. We then…

Machine Learning · Computer Science 2018-06-13 Jonathan Uesato , Brendan O'Donoghue , Aaron van den Oord , Pushmeet Kohli