LGCRMLNov 2, 2018

TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks

arXiv:1811.01031v321 citations
Originality Highly original
AI Analysis

This addresses security vulnerabilities in autonomous driving systems by creating stealthy attacks that bypass current detection methods.

The paper tackles the problem of generating imperceptible security attacks on deep neural networks without needing training data, achieving successful misclassification in traffic sign detection while remaining undetectable in quality tests.

Most of the data manipulation attacks on deep neural networks (DNNs) during the training stage introduce a perceptible noise that can be catered by preprocessing during inference or can be identified during the validation phase. Therefore, data poisoning attacks during inference (e.g., adversarial attacks) are becoming more popular. However, many of them do not consider the imperceptibility factor in their optimization algorithms, and can be detected by correlation and structural similarity analysis, or noticeable (e.g., by humans) in a multi-level security system. Moreover, the majority of the inference attack relies on some knowledge about the training dataset. In this paper, we propose a novel methodology which automatically generates imperceptible attack images by using the back-propagation algorithm on pre-trained DNNs, without requiring any information about the training dataset (i.e., completely training data-unaware). We present a case study on traffic sign detection using the VGGNet trained on the German Traffic Sign Recognition Benchmarks dataset in an autonomous driving use case. Our results demonstrate that the generated attack images successfully perform misclassification while remaining imperceptible in both "subjective" and "objective" quality tests.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes