Vision sensors are becoming increasingly ubiquitous, and they continuously collect, store, communicate, and process vast amount of sensitive data that are vulnerable to being stolen and misused. Existing cryptosystems based on complex cipher algorithms generally require extensive computational resources, making them difficult to use in vision sensors that have limited processing capabilities. Here, we propose and experimentally demonstrate a novel in situ image cryptography scheme based on a neuromorphic vision sensor comprising all-optically controlled (AOC) memristors. Due to the unique light wavelength and irradiation history-dependent bidirectional persistent photoconductivity of AOC memristors, a visual image can be stored, encrypted, decrypted, denoised, and destroyed within a vision sensor. A decrypted image can be encoded in situ and then accurately recognized through a memristive neural network. Encrypted and destroyed images are capable of withstanding hacking attacks even with trained neural networks. Our cryptography scheme enables complete cryptographic operations entirely on a sensor and, therefore, effectively safeguards visual information. This work provides a simple yet efficient solution to the security challenges faced by vision sensors.

中文翻译：

---

基于光驱动忆阻器的神经形态视觉传感器中的原位加密

视觉传感器变得越来越普遍，它们不断收集、存储、通信和处理大量容易被窃取和滥用的敏感数据。基于复杂密码算法的现有密码系统通常需要大量计算资源，这使得它们难以在处理能力有限的视觉传感器中使用。在这里，我们提出并实验演示了一种基于包含全光控制（AOC）忆阻器的神经形态视觉传感器的新型原位图像加密方案。由于 AOC 忆阻器具有独特的光波长和依赖于照射历史的双向持久光电导性，因此可以在视觉传感器内存储、加密、解密、去噪和销毁视觉图像。解密的图像可以在原位编码，然后通过忆阻神经网络准确识别。即使使用训练有素的神经网络，加密和破坏的图像也能够抵御黑客攻击。我们的加密方案可以完全在传感器上进行完整的加密操作，因此可以有效地保护视觉信息。这项工作为视觉传感器面临的安全挑战提供了一种简单而有效的解决方案。