ABSTRACT
Recent advances in resistive synaptic devices have enabled the emergence of brain-inspired smart chips. These chips can execute complex cognitive tasks in digital signal processing precisely and efficiently using an efficient neuromorphic system. The neuromorphic synapses used in such chips, however, are very sensitive to the external environment, thereby weakening their resistance to malicious modifications such as hardware Trojans and backdoors. Accordingly, in this paper, we propose HTcatcher, a security verification technique for hardware threat detection in neuromorphic computing systems, incorporating finite state machine and feature verification simultaneously, which has never been considered in prior work. Furthermore, we propose a pseudo-random matrix verifying technique for memory optimization, which can reduce the memory overhead of the multi-dimensional features in the system significantly. Experimental results confirm that the proposed method can identify the malicious modifications in the system accurately, while reducing the memory usage by 25%-50%.
Supplemental Material
- D. S. Modha. Neuromorphic and synaptronic spiking neural network with synaptic weights learned using simulation. U.S. Patent, 8,515,885, 2013--8--20.Google Scholar
- P. Yao, H. Wu, B. Gao, et al. Face classification using electronic synapses. Nature Communications., vol. 8, no. 15199, doi: 10.1038/ncomms151992017, 2017.Google Scholar
- Jiang Y, Huang P, Zhu D, et al. Design and hardware implementation of neuromorphic systems with RRAM synapses and threshold-controlled neurons for pattern recognition. IEEE Transactions on Circuits and Systems I, vol. 65, no. 9, pp. 2726--2738, 2018.Google ScholarCross Ref
- Ielmini, Daniele. Brain-inspired computing with resistive switching memory (RRAM): Devices, synapses and neural networks. Microelectronic Engineering., vol. 190, pp. 44--53, 2018.Google ScholarCross Ref
- S. Yu, Y. Wu, et al. An electronic synapse device based on metal oxide resistive switching memory for neuromorphic computation. IEEE Trans on Electron Devices, vol. 58, no. 8, pp. 2729--2737, 2011.Google ScholarCross Ref
- R. C. Rodrigo, L. Javier and G. Stefanos. Evolution and trends in IoT security. Computer, vol. 51, no. 7, pp. 16--25, 2018.Google ScholarCross Ref
- M. Li, B. Yu, Y. Lin, et al. A practical split manufacturing framework for Trojan prevention via simultaneous wire lifting and cell insertion. proc. of ASP-DAC, 2018, pp. 256--270.Google ScholarCross Ref
- Beringuierboher N, Lacruche M, Elbaze D, et al. Body biasing injection attacks in practice. Proceedings of the Third Workshop on Cryptography and Security in Computing Systems, 2016, pp. 49--54.Google ScholarDigital Library
- Yang K, Hicks M, Dong Q, et al. Exploiting the analog properties of digital circuits for malicious hardware. Communications of the ACM, vol. 60, no. 9, pp. 83--91, 2017.Google ScholarDigital Library
- N. Beringuier-Boher, H. David, V. Beroulle, et al. Increasing the security level of analog IPs by using a dedicated vulnerability analysis methodology. proc. of ISQED, 2013.Google ScholarCross Ref
- Hassan Salmani. COTD: reference-free hardware Trojan detection and recovery based on controllability and observability in gate-level Netlist. IEEE Transactions on Information Forensics & Security, vol. 12, no. 2, pp. 338--350, 2017.Google ScholarDigital Library
- B. Liu, C. Yang, H. Li, et al. Security of neuromorphic systems: challenges and solutions. proc. of ISCAS, 2016, pp. 1326--1329.Google ScholarCross Ref
- L. X. Xia, et al. Fault-tolerant training enabled by on-line fault detection for RRAM-based neural computing systems. IEEE Trans on Computer-Aided Design of Integrated Circuits and Systems., 2018.Google Scholar
- S. Zhang, G. L. Zhang, B. Li, H. H. Li and U. Schlichtmann. Aging-aware lifetime enhancement for memristor-based neuromorphic computing. proc. of DATE, 2019, pp. 1751--1756.Google ScholarCross Ref
- Y. Zhu, G. L. Zhang, T. Wan, B. Li, Y. Shi, T.-Y. Ho and U. Schlichtmann. Statistical training for neuromorphic computing using memristor-based crossbars considering process variations and noise. proc. of DATE, 2020Google ScholarCross Ref
- Dong C, Zhang F, Liu X, et al. A locating method for multi-purposes HTs based on the boundary network. IEEE Access, vol.7, pp. 110936--110950, 2019.Google ScholarCross Ref
- Q. Liu, T. Liu, Z. Liu, et al. Security analysis and enhancement of model compressed deep learning systems under adversarial attacks. proc. of ASP-DAC, 2018, pp. 721--7Google ScholarCross Ref
- A. Sengupta, D. Roy, S. P. Mohanty. Triple-phase watermarking for reusable IP core protection during architecture synthesis. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems., vol. 37, no. 4, pp. 742--755, 2018.Google ScholarDigital Library
- J. Magana, D. Shi, J. Melchert, et al. Are proximity attacks a threat to the security of split manufacturing of integrated circuits?IEEE Transactions on Very Large Scale Integration (VLSI) Systems., vol. 25, no. 12, pp. 3406--3419, 2017.Google Scholar
- M. Oya, N. Yamashita, T. Okamura, et al. Hardware-trojans rank: quantitative evaluation of security threats at gate-level netlists by pattern matching. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences,vol. E99, no. A(12), pp. 2335--2347, 2016.Google Scholar
- H. Ding, J. Wang and J. Zhong. Temperature-variation based hardware trojan detection through ring oscillator. Electronics Letters, vol. 52, no. 15, pp. 1302--1304, 2016.Google ScholarCross Ref
- Hassan Salmani. Hardware trojans in analog and mixed-signal integrated circuits. Trusted Digital Circuits, pp. 121--131. Springer, 2018.Google ScholarCross Ref
- R. S. Chakraborty, S. Pagliarini, J. Mathew, et al. A flexible online checking technique to enhance hardware trojan horse detectability by reliability analysis. IEEE Transactions on Emerging Topics in Computing, vol. 5, no. 2, pp. 260--270, 2017.Google ScholarCross Ref
- A. V. Karthik, et al. ABCD-NL: Approximating continuous non-linear dynamical systems using purely boolean models for analog/mixed-signal verification. proc. of ASP-DAC, 2014, pp. 250--255.Google ScholarCross Ref
- Karthik A V, et al. ABCD-L: Approximating continuous linear systems using Boolean models. proc. of DAC, 2013, pp. 1--9.Google Scholar
- M. Bidmeshki, A. Antonopoulos, Y. Makris. Information flow tracking in analog/mixed-signal designs through proof-carrying hardware IP. proc. of DATE, 2017, pp. 1703--1708.Google ScholarCross Ref
- K. Yang, M. Hicks, Q. Dong, et al. A2: Analog malicious hardware. proc. of SP, 2016, pp. 18--37.Google ScholarCross Ref
- Hashemi S, Tann H, Reda S. BLASYS: Approximate logic synthesis using boolean matrix factorization. proc. of DAC, 2018, pp. 1--6.Google Scholar
Index Terms
- HTcatcher: Finite State Machine and Feature Verifcation for Large-scale Neuromorphic Computing Systems
Recommendations
A neuromimetic realization of hippocampal CA1 for theta wave generation
AbstractRecent advances in neural engineering allowed the development of neuroprostheses which facilitate functionality in people with neurological problems. In this research, a real-time neuromorphic system is proposed to artificially ...
Application the Spiking Neuron Model with Structural Adaptation to Describe Neuromorphic Systems
The paper discusses the architectural elements of neuromorphic systems on the example of behaviour control of robots. The basis of the work is new spiking neuron model, which allows describing the known biological network relying on macroscopic ...
Hardware design of LIF with Latency neuron model with memristive STDP synapses
In this paper, the hardware implementation of a neuromorphic system is presented. This system is composed of a Leaky Integrate-and-Fire with Latency (LIFL) neuron and a Spike-Timing Dependent Plasticity (STDP) synapse. LIFL neuron model allows to encode ...
Comments