Related papers: Robustness from Simple Classifiers

Robustness from Simple Classifiers

URL: http://arxiv.org/abs/2002.09422v1
Date: Fri, 21 Feb 2020 17:13:37 GMT
Title: Robustness from Simple Classifiers
Authors: Sharon Qian, Dimitris Kalimeris, Gal Kaplun, Yaron Singer
Abstract summary: We investigate the connection between robustness and simplicity. We find that simpler classifiers, formed by reducing the number of output classes, are less susceptible to adversarial perturbations.
Score: 31.50446148110293
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Despite the vast success of Deep Neural Networks in numerous application domains, it has been shown that such models are not robust i.e., they are vulnerable to small adversarial perturbations of the input. While extensive work has been done on why such perturbations occur or how to successfully defend against them, we still do not have a complete understanding of robustness. In this work, we investigate the connection between robustness and simplicity. We find that simpler classifiers, formed by reducing the number of output classes, are less susceptible to adversarial perturbations. Consequently, we demonstrate that decomposing a complex multiclass model into an aggregation of binary models enhances robustness. This behavior is consistent across different datasets and model architectures and can be combined with known defense techniques such as adversarial training. Moreover, we provide further evidence of a disconnect between standard and robust learning regimes. In particular, we show that elaborate label information can help standard accuracy but harm robustness.

Related papers

MOREL: Enhancing Adversarial Robustness through Multi-Objective Representation Learning [1.534667887016089]
deep neural networks (DNNs) are vulnerable to slight adversarial perturbations. We show that strong feature representation learning during training can significantly enhance the original model's robustness. We propose MOREL, a multi-objective feature representation learning approach, encouraging classification models to produce similar features for inputs within the same class, despite perturbations.
arXiv Detail & Related papers (2024-10-02T16:05:03Z)
Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off [0.6554326244334868]
We argue that a good approximation of the sensitivity to adversarial perturbations requires significantly more effort than what is currently considered satisfactory. We propose new attacks and combine them with the strongest attacks available in the literature. Our results also demonstrate that a diverse set of strong attacks is necessary, because different models are often vulnerable to different attacks.
arXiv Detail & Related papers (2024-07-12T10:32:53Z)
Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
arXiv Detail & Related papers (2023-03-24T16:03:21Z)
What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study [8.912245110734334]
This work studies what information the adversarially trained model focuses on. We consider two common ways to improve model robustness, namely, by data augmentation and by using stronger network architectures.
arXiv Detail & Related papers (2022-03-16T16:37:17Z)
Clustering Effect of (Linearized) Adversarial Robust Models [60.25668525218051]
We propose a novel understanding of adversarial robustness and apply it on more tasks including domain adaption and robustness boosting. Experimental evaluations demonstrate the rationality and superiority of our proposed clustering strategy.
arXiv Detail & Related papers (2021-11-25T05:51:03Z)
Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
arXiv Detail & Related papers (2021-02-23T20:59:30Z)
Stylized Adversarial Defense [105.88250594033053]
adversarial training creates perturbation patterns and includes them in the training set to robustify the model. We propose to exploit additional information from the feature space to craft stronger adversaries. Our adversarial training approach demonstrates strong robustness compared to state-of-the-art defenses.
arXiv Detail & Related papers (2020-07-29T08:38:10Z)
Adversarial Self-Supervised Contrastive Learning [62.17538130778111]
Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions. We propose a novel adversarial attack for unlabeled data, which makes the model confuse the instance-level identities of the perturbed data samples. We present a self-supervised contrastive learning framework to adversarially train a robust neural network without labeled data.
arXiv Detail & Related papers (2020-06-13T08:24:33Z)
Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness [97.67477497115163]
We use mode connectivity to study the adversarial robustness of deep neural networks. Our experiments cover various types of adversarial attacks applied to different network architectures and datasets. Our results suggest that mode connectivity offers a holistic tool and practical means for evaluating and improving adversarial robustness.
arXiv Detail & Related papers (2020-04-30T19:12:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.