Brief

Researchers have developed PoTAcc, an open-source pipeline designed to accelerate the deployment of power-of-two (PoT) quantized deep neural networks (DNNs) on resource-constrained edge devices. This system facilitates the preparation and deployment of these models through TensorFlow Lite, supporting both CPU-only configurations and hybrid CPU-FPGA systems with custom accelerators. Evaluations demonstrated that a CPU-accelerator design using PoTAcc achieved up to a 3.6x speedup and a 78% reduction in energy consumption compared to CPU-only execution on specific FPGA boards. AI

Researchers have developed a new method called AdaLoc to enhance the security of deep neural networks (DNNs) by embedding an access key within a subset of the model's parameters. This approach allows for adaptable model usage control, meaning that even after fine-tuning or task-specific updates, the model's utility can be restored to authorized states without requiring a full re-keying process. Experiments across various benchmarks and architectures demonstrate AdaLoc's effectiveness in maintaining high accuracy for authorized users while significantly degrading performance for unauthorized access, dropping it to near-random guessing levels. AI