DeepiSign: Invisible Fragile Watermark to Protect the Integrityand Authenticity of CNN

@article{Abuadbba2021DeepiSignIF,
  title={DeepiSign: Invisible Fragile Watermark to Protect the Integrityand Authenticity of CNN},
  author={A. Abuadbba and Hyoungshick Kim and S. Nepal},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.04319}
}
Convolutional Neural Networks (CNNs) deployed in real-life applications such as autonomous vehicles have shown to be vulnerable to manipulation attacks, such as poisoning attacks and fine-tuning. Hence, it is essential to ensure the integrity and authenticity of CNNs because compromised models can produce incorrect outputs and behave maliciously. In this paper, we propose a self-contained tamper-proofing method, called DeepiSign, to ensure the integrity and authenticity of CNN models against… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 28 REFERENCES
Protecting Intellectual Property of Deep Neural Networks with Watermarking
  • 110
  • PDF
Digital image steganography: Survey and analysis of current methods
  • 1,422
  • PDF
Embedding Watermarks into Deep Neural Networks
  • 124
  • PDF
VerIDeep: Verifying Integrity of Deep Neural Networks through Sensitive-Sample Fingerprinting
  • 5
  • PDF
Adversarial frontier stitching for remote neural network watermarking
  • 79
  • PDF
Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
  • 133
  • Highly Influential
  • PDF
DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Models
  • 51
  • Highly Influential
  • PDF
Wavelet based steganographic technique to protect household confidential information and seal the transmitted smart grid readings
  • 21
Digital watermarking for deep neural networks
  • 46
  • PDF
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
  • 226
  • PDF
...
1
2
3
...