paper-with-me

Papers

Localized Adversarial Training for Increased Accuracy and Robustness in Image Classification

2019-09-10 · Eitan Rothberg, Tingting Chen, Luo Jie, Hao Ji

Today's state-of-the-art image classifiers fail to correctly classify carefully manipulated adversarial images. In this work, we develop a new, localized adversarial attack that generates adversarial examples by imperceptibly altering the backgrounds of normal images. We first use this attack to highlight the unnecessary sensitivity of neural networks to changes in the background of an image, then use it as part of a new training technique: localized adversarial training. By including locally adversarial images in the training set, we are able to create a classifier that suffers less loss than a non-adversarially trained counterpart model on both natural and adversarial inputs. The evaluation of our localized adversarial training algorithm on MNIST and CIFAR-10 datasets shows decreased accuracy loss on natural images, and increased robustness against adversarial inputs.

📄 PDF Abstract BibTeX arXiv:1909.04779

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackGeneral Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses

2022-11-10 · Abhiram Kolli, Muhammad Jehanzeb Mirza, Horst Possegger, Horst Bischof

Keyless entry systems in cars are adopting neural networks for localizing its operators. Using test-time adversarial defences equip such systems with the ability to defend against adversarial attacks without prior traini…

Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions

2025-04-02 · Giulia Marchiori Pietrosanti, Giulio Rossolini, Alessandro Biondi, Giorgio Buttazzo

The robustness of DNNs is a crucial factor in safety-critical applications, particularly in complex and dynamic environments where localized corruptions can arise. While previous studies have evaluated the robustness of …

BenchmarkingSegmentationSemantic Segmentation

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers

2021-10-27 · NeurIPS 2021 12 · Husheng Han, Kaidi Xu, Xing Hu, Xiaobing Chen 외

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses tow…

Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy

2021-03-15 · Bronya Roni Chernyak, Bhiksha Raj, Tamir Hazan, Joseph Keshet

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood aro…

Adversarial Robustness

Introducing Adaptive Continuous Adversarial Training (ACAT) to Enhance ML Robustness

2024-03-15 · Mohamed elShehaby, Aditya Kotha, Ashraf Matrawy

Adversarial training enhances the robustness of Machine Learning (ML) models against adversarial attacks. However, obtaining labeled training and adversarial training data in network/cybersecurity domains is challenging …

Spam detection