PoTrojan: powerful neural-level trojan designs in deep learning models
Explore this paper's citation graph
Summary
This paper proposes a novel approach to design and insert powerful neural-level trojans or PoTrojan in pre-trained NN models, and explains the principles of PoTrojans and the easiness of designing and inserting them inPre-trained deep learning models.
- Type
- preprint
- Published
- 2018-02-08
- Cited by
- 63
- References
- 16
- Access
- Open access
- OpenAlex
- https://openalex.org/W2785405530
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:3636228
Keywords
Artificial intelligence, Artificial neural network, Computer science, Deep learning, Trojan
References
- Neural network Trojan
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- ImageNet Large Scale Visual Recognition Challenge
- A Survey of Hardware Trojan Taxonomy and Detection
- ImageNet classification with deep convolutional neural networks
- Mastering the game of Go with deep neural networks and tree search
- Deep residual learning for image steganalysis
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Robust Physical-World Attacks on Deep Learning Models
- Trojaning Attack on Neural Networks
Cited by
- How To Backdoor Federated Learning
- VerIDeep: Verifying Integrity of Deep Neural Networks through Sensitive-Sample Fingerprinting
- Latent Surgical Interventions in Residual Neural Networks
- FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning
- ISA4ML: Training Data-Unaware Imperceptible Security Attacks on Machine Learning Modules of Autonomous Vehicles
- RED-Attack: Resource Efficient Decision based Attack for Machine Learning
- TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks
- Are You Tampering With My Data?
- A Stealthy Hardware Trojan Exploiting the Architectural Vulnerability of Deep Learning Architectures: Input Interception Attack (IIA)
- ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation
- STRIP: a defence against trojan attacks on deep neural networks
- Backdoor Attacks Against Transfer Learning With Pre-Trained Deep Learning Models
- Robust Machine Learning Systems: Challenges,Current Trends, Perspectives, and the Road Ahead
- Exposing Backdoors in Robust Machine Learning Models
- The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models
- Machine Learning Security: Threats, Countermeasures, and Evaluations
- Blind Backdoors in Deep Learning Models
- TBT: Targeted Neural Network Attack With Bit Trojan
- How Secure is Distributed Convolutional Neural Network on IoT Edge Devices?
- Security Enhancement for RRAM Computing System through Obfuscating Crossbar Row Connections
Related papers
- Review on Research of Marxism Popularity in 2008
- The Dynamics of the Trojan Asteroids
- Interpretable Mesomorphic Networks for Tabular Data
- Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications
- Deep learning: Evolution and expansion
- Multi-Condition Training on Deep Convolutional Neural Networks for Robust Plant Diseases Detection