PoTrojan: powerful neural-level trojan designs in deep learning models

Abstract

With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many areas of human life. Neural network or artificial neural network (NN), the main technique behind DL, has been extensively studied to facilitate computer vision and natural language recognition. However, the more we rely on information technology, the more vulnerable we are. That is, malicious NNs could bring huge threat in the so-called coming AI era. In this paper, for the first time in the literature, we propose a novel approach to design and insert powerful neural-level trojans or PoTrojan in pre-trained NN models. Most of the time, PoTrojans remain inactive, not affecting the normal functions of their host NN models. PoTrojans could only be triggered in very rare conditions. Once activated, however, the PoTrojans could cause the host NN models to malfunction, either falsely predicting or classifying, which is a significant threat to human society of the AI era. We would explain the principles of PoTrojans and the easiness of designing and inserting them in pre-trained deep learning models. PoTrojans doesn't modify the existing architecture or parameters of the pre-trained models, without re-training. Hence, the proposed method is very efficient.

arXiv comment7 pages, 6 figures

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Robust Physical-World Attacks on Deep Learning Models

Cited by in corpus (15)

• How To Backdoor Federated Learning
• Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
• STRIP: A Defence Against Trojan Attacks on Deep Neural Networks
• Robust Backdoor Attacks against Deep Neural Networks in Real Physical World
• TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks
• The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models
• Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks
• FeSHI: Feature Map Based Stealthy Hardware Intrinsic Attack
• RED-Attack: Resource Efficient Decision based Attack for Machine Learning
• VerIDeep: Verifying Integrity of Deep Neural Networks through Sensitive-Sample Fingerprinting
• TBT: Targeted Neural Network Attack with Bit Trojan
• A Stealthy Hardware Trojan Exploiting the Architectural Vulnerability of Deep Learning Architectures: Input Interception Attack (IIA)
• How Secure is Distributed Convolutional Neural Network on IoT Edge Devices?
• Blackbox Trojanising of Deep Learning Models : Using non-intrusive network structure and binary alterations
• FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning