With the rapid development of the Internet of Things (IoT), compute-in-memory (CIM) is a promising candidate for edge computing, which eliminates the need for frequent data transfer between the memory and processing units. On one hand, CIM provides an efficient approach to achieve deep neural network (DNN) inference; on the other hand, its security issues such as model leakage are ignored in most of state-of-the-art studies. In the resource-limited conditions, it is essential to develop a lightweight secure scheme for CIM without significantly sacrificing its performance. In this work, a physical unclonable function (PUF)-CIM macro based on static random access memory (SRAM) is proposed for lightweight model protection. An SRAM-based PUF extracts unique and stable keys from the mismatch of multirow discharge rate and further achieves zero bit error rate (BER) under temperature and voltage fluctuations by the on-chip masking technique. Besides, we propose a 10T SRAM bit cell to perform xor operation and multiply-and-accumulate (MAC) operation in the same cell, which avoids weight movement during encryption and decryption. The whole process including key generation, xor encryption, and ciphertext MAC operation has been realized. The test chip is designed and fabricated in a 55-nm CMOS process. Experimental results show that the proposed PUF with on-chip masking can provide zero unstable bits and BER under temperature and voltage variations. The proposed PUF-CIM achieves 96.20% inference accuracy in MNIST. Besides, it presents 93.35–121.38-TOPS/W energy efficiency and 1324.24-GOPS throughput. Compared with the normal CIM, the proposed PUF-CIM can enhance AI model security, only with accuracy loss of 1% and energy efficiency degradation of 16.1%.
28 December 2023 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Physical unclonable function (PUF) is an innovative primitive used for key generation and device authentication, which has promising applications for resource-limited scenarios such as satellite communication. However, the reliability of traditional PUF circuits is low and the power consumption is high. Maintaining reliability also requires high costs, which limits its practical application. This article proposes a multimode SRAM PUF based on a 55-nm CMOS process, which has a self-healing feature. By using a voltage tilt preselection mechanism, the unstable PUF cells can be detected and most of them can be healed by mode switching, thereby improving the reliability of the PUF and reducing the costs required for golden key screening tests. However, the total ionizing dose (TID) effect poses a threat to the PUF, which can significantly increase the bit error rate (BER). In this article, the radiation effect of the PUF is characterized and its mechanism is analyzed. Besides, by means of the self-healing and preirradiation temperature and voltage masking techniques, the radiation reliability of the proposed PUF can be improved avoiding traditional destructive testing. The experimental results demonstrate that the BER can be reduced to as low as 0.0183%, which is 345 $\times$ lower than the raw BER, after irradiation up to 100 krad(Si). The proposed technique presents great potential for communication security in the aerospace environment.
Recently, with the rapid development of underwater resource exploration and underwater activities, underwater acoustic (UA) target recognition has become crucial in marine resource exploration. However, traditional underwater acoustic recognition systems face challenges such as low energy efficiency, poor accuracy, and slow response times. Systems for UA target recognition using deep learning networks have garnered widespread attention. Convolutional neural network (CNN) consumes significant computational resources and energy during convolution operations, which exacerbates the issues of energy consumption and complicates edge deployment. This paper explores a high-energy-efficiency UA target recognition system. Based on the DenseNet CNN, the system uses fine-grained pruning for sparsification and sparse convolution computations. The UA target recognition CNN was deployed on FPGAs and chips to achieve low-power recognition. Using the noise-disturbed ShipsEar dataset, the system reaches a recognition accuracy of 98.73% at 0 dB signal-to-noise ratio (SNR). After 50% fine-grained pruning, the accuracy is 96.11%. The circuit prototype on FPGA shows that the circuit achieves an accuracy of 95% at 0 dB SNR. This work implements the circuit design and layout of the UA target recognition chip based on a 65 nm CMOS process. DC synthesis results show that the power consumption is 90.82 mW, and the single-target recognition time is 7.81 ns.
7 January 2025 in IEEE Transactions on Nuclear Science
Compute-in-memory (CIM) with high parallelism and energy efficiency is an attractive solution for next-generation orbital edge computing. However, the reliability of the CIM circuits in radiation environment is rarely studied. In this paper, we present an analog CIM macro based on Static Random-Access Memory (SRAM) in a 55-nm CMOS process, featuring multiply-accumulate (MAC) operations. The performance degradation including computational linearity and MAC operation accuracy is evaluated by means of γ-ray irradiation experiment. The mechanism of radiation effect of the analog CIM is revealed and a Radiation-Induced Calculation Error (RICE) model is proposed. The simulation results show that the accuracy of MAC operation decreases by about 5% after irradiation to 250 krad(Si), in good agreement with the measurement results. This paper provides guidance for the design and application of SRAM-based CIM processors in the radiation environment.
Recently, with the rapid development of underwater resource exploration and underwater activities, Underwater Acoustic (UA) target recognition has become crucial in marine resource exploration. However, traditional underwater acoustic recognition systems face challenges such as low energy efficiency, poor accuracy, and slow response times. Systems for UA target recognition using deep learning networks have garnered widespread attention. Convolutional neural network (CNN) consumes significant computational resources and energy during convolution operations, which exacerbates the issues of energy consumption and complicates edge deployment. This paper explores a high-energy-efficiency UA target recognition system. Based on the DenseNet CNN, the system uses fine-grained pruning for sparsification and sparse convolution computations. The UA target recognition CNN was deployed on FPGAs and chips to achieve low-power recognition. Using the Noise-disturbed ShipsEar dataset, the system reaches a recognition accuracy of 98.73% at 0dB signal-to-noise ratio (SNR). After 50% fine-grained pruning, the accuracy is 96.11%. The circuit prototype on FPGA shows that the circuit achieves an accuracy of 95% at 0dB SNR. This work implements the circuit design and layout of the UA target recognition chip based on a 65nm CMOS process. DC synthesis results show the power consumption is 90.82mW, and the single-target recognition time is 7.81ns.