利用类脑芯片的不确定性，实现隐蔽入侵的新型攻击方法
Neuromorphic Mimicry Attacks Exploiting Brain-Inspired Computing for Covert Cyber Intrusions
- 通过篡改突触权重和污染输入信号模仿正常神经活动
- 在模拟类脑芯片数据集上成功绕过传统检测系统
- 适合关注类脑计算安全的科研与工业从业者
类脑计算受人脑神经架构启发，以低功耗、自适应和事件驱动设计革新人工智能与边缘计算。然而，其独特特性也引入新型网络安全风险。本文提出类脑模仿攻击（NMAs），一类利用类脑芯片概率性与非确定性特征实施隐蔽入侵的突破性威胁。通过突触权重篡改和感官输入污染等技术，NMAs可模仿合法神经活动，规避传统入侵检测系统，对自动驾驶、智能医疗植入设备及物联网网络构成威胁。研究构建了NMAs的理论框架，基于模拟类脑芯片数据集评估其影响，并提出神经特异性异常检测与安全突触学习协议等防御措施。结果凸显了针对类脑计算定制化安全防护的紧迫性，为这一新兴威胁领域提供了开创性探索。
原文摘要 · Abstract (English)
Neuromorphic computing, inspired by the human brain's neural architecture, is revolutionizing artificial intelligence and edge computing with its low-power, adaptive, and event-driven designs. However, these unique characteristics introduce novel cybersecurity risks. This paper proposes Neuromorphic Mimicry Attacks (NMAs), a groundbreaking class of threats that exploit the probabilistic and non-deterministic nature of neuromorphic chips to execute covert intrusions. By mimicking legitimate neural activity through techniques such as synaptic weight tampering and sensory input poisoning, NMAs evade traditional intrusion detection systems, posing risks to applications such as autonomous vehicles, smart medical implants, and IoT networks. This research develops a theoretical framework for NMAs, evaluates their impact using a simulated neuromorphic chip dataset, and proposes countermeasures, including neural-specific anomaly detection and secure synaptic learning protocols. The findings underscore the critical need for tailored cybersecurity measures to protect brain-inspired computing, offering a pioneering exploration of this emerging threat landscape.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。