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

Abstract

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.

References in corpus (10)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• End to End Learning for Self-Driving Cars
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• A Roadmap Towards Resilient Internet of Things for Cyber-Physical Systems
• Data Poisoning Attacks against Online Learning
• PoTrojan: powerful neural-level trojan designs in deep learning models
• Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference
• RED-Attack: Resource Efficient Decision based Attack for Machine Learning

Cited by in corpus (6)

• Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
• Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead
• Blind Backdoors in Deep Learning Models
• Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
• QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks
• FeSHI: Feature Map Based Stealthy Hardware Intrinsic Attack