Resource Efficient Deep Learning Hardware Watermarks with Signature Alignment

Deep learning intellectual properties (IPs) are high-value assets that are frequently susceptible to theft. This vulnerability has led to significant interest in defending the field's intellectual properties from theft. Recently, watermarking techniques have been extended to protect deep learning hardware from privacy. These technique embed modifications that change the hardware's behavior when activated. In this work, we propose the first method for embedding watermarks in deep learning hardware that incorporates the owner's key samples into the embedding methodology. This improves our watermarks' reliability and efficiency in identifying the hardware over those generated using randomly selected key samples. Our experimental results demonstrate that by considering the target key samples when generating the hardware modifications, we can significantly increase the embedding success rate while targeting fewer functional blocks, decreasing the required hardware overhead needed to defend it.

Authors

• Joseph Clements Clemson University, Clemson, South Carolina, 29634 Applied Research Associates, Albuquerque, New Mexico, 87110
• Yingjie Lao Clemson University, Clemson, South Carolina, 29634 Tufts University, Medford, Massachusetts, 02155

Keywords

• ML: Adversarial Learning & Robustness
• ML: Ethics, Bias, and Fairness