Real-time intrusion detection with millisecond response is critical for Internet of Vehicles (IoV) security but is challenged by extreme class imbalance and high computational costs. This paper proposes a novel multimodal framework integrating Denoising Diffusion Probabilistic Models (DDPM) and Knowledge Distillation (KD). First, multi-source data is transformed into RGB images. A conditional DDPM with timestep and class embeddings balances datasets by generating minority-class samples. The teacher model (DiffuGuardian) fuses text-image features for training. Subsequently, a lightweight student model, LiteSentinel, is designed employing depthwise separable convolutions and inverted residual blocks to reduce parameters. Results on three datasets demonstrate that DiffuGuardian consistently achieves around 98–100% precision, accuracy, recall, and F1-score under 5-fold evaluation, while LiteSentinel maintains approximately 95–99% across all metrics with substantially reduced complexity. DiffuGuardian reaches an inference time of 3.80ms with a model size of 0.10 MB, whereas LiteSentinel further reduces latency to 0.79ms with a size of 0.07 MB, enabling efficient edge deployment for IoV security.

ABSTRACT With the introduction of the concept of smart cities and the widespread application of drones in areas such as traffic monitoring, air quality monitoring, and emergency medical response, the rapid development and emergence of the Internet of Drones (IoD) have been driven forward. Drones, as a critical component of IoD, leverage their advantage in airspace coverage and real‐time dynamic response capabilities. Through the IoD framework, they enable multi‐drone collaboration and real‐time data sharing, making them an essential part of smart cities. However, drones, as resource‐constrained devices, are unable to perform overly complex computations or utilize public‐key cryptographic techniques. Therefore, we have designed a lightweight authentication and key agreement scheme based on Physical Unclonable Function (PUF) for the smart city environment. By completing the user registration phase over a public channel, it is better suited for the actual deployment of IoD in smart cities. Using the Real‐or‐Random (RoR) model and the widely recognized formal analysis tool ProVerif, we conducted a formal analysis of the proposed scheme, ensuring its security. We also evaluated the computational cost and communication overhead of the designed scheme. The results show that the proposed scheme is better suited for IoD‐based smart city environments, offering lower computational costs, reduced communication overhead, and improved security.

As a subset of discrete Fourier transform (DFT), discrete cosine transform (DCT), especially two-dimensional discrete cosine transform (2D-DCT), is an important mathematical tool for digital signal processing. However, the computational complexity of 2D-DCT is quite high, which makes it impossible to meet the requirements in some signal processing fields with large signal sizes. In addition, to optimize the 2D-DCT algorithm itself, seeking help from a cloud platform is considered to be an excellent alternative to dramatically speeding up 2D-DCT operations. Still, there are three key challenges in cloud computing outsourcing that need to be addressed, including protecting the privacy of input and output data, ensuring the correctness of the returned results, and ensuring adequate local cost savings. In this paper, we explore the design of a practical outsourcing protocol for 2D-DCT and 2D-IDCT, which well solves the above three challenges. Both theoretical analysis and simulation experiment results not only confirm the feasibility of the proposed protocol but also show its outstanding performance in efficiency.