Probabilistic Jacobian-based Saliency Maps Attacks

Combey, Théo; Loison, António; Faucher, Maxime; Hajri, Hatem

doi:10.48550/arxiv.2007.06032

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By identifying and suppressing these irregular patterns within localized regions, LGS can potentially neutralize the adversarial effect. Another detection strategy leverages saliency maps to pinpoint areas of the image that exhibit unusual activation patterns or deviate from the expected distribution of saliency in clean images [27], [28]. These flagged regions might indicate the presence of a local distortion.…”

Section: Distortion Attack Defencesmentioning

confidence: 99%

Immunizing Image Classifiers Against Localized Adversary Attack

Ghebrechristos,

Alaghband

2024

IJAIA

View full text Add to dashboard Cite

This paper addresses the vulnerability of deep learning models, particularly convolutional neural networks (CNN)s, to adversarial attacks and presents a proactive training technique designed to counter them. We introduce a novel volumization algorithm, which transforms 2D images into 3D volumetric representations. When combined with 3D convolution and deep curriculum learning optimization (CLO), it significantly improves the immunity of models against localized universal attacks by up to 40%. We evaluate our proposed approach using contemporary CNN architectures and the modified Canadian Institute for Advanced Research (CIFAR-10 and CIFAR-100) and ImageNet Large Scale Visual Recognition Challenge (ILSVRC12) datasets, showcasing accuracy improvements over previous techniques. The results indicate that the combination of the volumetric input and curriculum learning holds significant promise for mitigating adversarial attacks without necessitating adversary training.

show abstract

Section: Distortion Attack Defencesmentioning

confidence: 99%