Scholarlink

<p>With the rapid proliferation of IoT devices and its growing usage in safety-critical systems, securing these devices from malicious attacks has become increasingly challenging. Due to the resource-constrained nature of IoT devices, real-time software-based malware detection is difficult or infeasible. Alternatively, a promising approach is utilizing hardware malware detection techniques. In this paper, we introduce a novel hardware immune system (HWIS), a stand-alone, hardware-supported malware detection approach for microprocessors that leverages artificial immune systems for detecting botnet activity. This technique is suitable for low-power, resource constrained and network facing embedded devices. The proposed model is capable of detecting botnet behavior with an accuracy of 96.7%, false negative rate of 6.5%, and F1-score of 0.96. We implemented and simulated the proposed architecture using 32nm low-power PTM SPICE models and the Synopsys 32nm EDK and found the power and area overhead to be 2.57% and 5.25%, respectively, with no impact on delay, using a 28nm RISC-V CPU as a baseline. We also synthesized the HWIS design on a Xilinx Virtex-7 FPGA using LUT-based RAM (4234 LUTs, 5732 flip-flops, 150 mW), with 7.7% and 12.5% logic and flip-flop overheads over the ROCKET RISC-V CPU. A hybrid BRAM+LUT version (1 BRAM, 2966 LUTs) used 155 mW and maintained 20 ns latency, optimizing memory and logic usage.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Malware Detection in Embedded Devices Using Artificial Hardware Immunity

  • 期刊论文

  • 发表日期：

    2025年8月13日

查看全文
  • Farhath Zareen,
  • Ahmed Ghoneim,
  • Mateus A. Fernandes A.,
  • Samir Ahmed,
  • Robert Karam

摘要

With the rapid proliferation of IoT devices and its growing usage in safety-critical systems, securing these devices from malicious attacks has become increasingly challenging. Due to the resource-constrained nature of IoT devices, real-time software-based malware detection is difficult or infeasible. Alternatively, a promising approach is utilizing hardware malware detection techniques. In this paper, we introduce a novel hardware immune system (HWIS), a stand-alone, hardware-supported malware detection approach for microprocessors that leverages artificial immune systems for detecting botnet activity. This technique is suitable for low-power, resource constrained and network facing embedded devices. The proposed model is capable of detecting botnet behavior with an accuracy of 96.7%, false negative rate of 6.5%, and F1-score of 0.96. We implemented and simulated the proposed architecture using 32nm low-power PTM SPICE models and the Synopsys 32nm EDK and found the power and area overhead to be 2.57% and 5.25%, respectively, with no impact on delay, using a 28nm RISC-V CPU as a baseline. We also synthesized the HWIS design on a Xilinx Virtex-7 FPGA using LUT-based RAM (4234 LUTs, 5732 flip-flops, 150 mW), with 7.7% and 12.5% logic and flip-flop overheads over the ROCKET RISC-V CPU. A hybrid BRAM+LUT version (1 BRAM, 2966 LUTs) used 155 mW and maintained 20 ns latency, optimizing memory and logic usage.