Deploying Vision Transformers (ViTs) in edge computing environments presents significant challenges due to their high computing demands and the resource constraints of edge devices. While collaborative edge computing and dynamic token dropping offer potential solutions, existing approaches suffer from rigid strategies that fail to adapt to diverse conditions of network and computing resources at the edge. This paper introduces EasyViT, an adaptive framework that optimizes ViT deployment through the joint coordination of collaborative edge computing and dynamic token dropping. Key innovations include: (1) A token dropping model that integrates dynamic token dropping and collaborative edge environments, formulating an integer linear programming (ILP) optimization problem. (2) An Approximate Stochastic Gradient Descent (ASGD) method with atomic gradient calculation, which transforms the NP-hard ILP problem into a continuous space for rapid near-optimal solution generation. Extensive evaluations on a real-world edge testbed with multiple Raspberry Pi nodes demonstrate that EasyViT achieves 1.06–5.06× speedup over baseline methods under 20 configurations of edge environments, while maintaining model accuracy within 2.8% degradation. The proposed framework exhibits the adaptability across diverse ViT architectures, network bandwidths, and computing resources.

Radio frequency fingerprint (RFF) identification is emerging as an attractive paradigm for physical layer security. Despite the exceptional accuracy achieved by deep learning (DL) based schemes, few works consider the cross-receiver scenario. The performance deteriorates significantly when the model is deployed on new receivers directly. To this end, a cross-receiver RFF learning scheme is proposed. First, an unsupervised pre-training method based on contrastive learning is utilized to extract receiver-agnostic features. Then, the model is optimized by subdomain adaptation to further improve identification performance. The proposed scheme does not require multiple labeled datasets from different receivers. And experimental results indicate that the proposed scheme effectively alleviates performance degradation in the cross-receiver scenario.

Specific emitter identification (SEI) is a technique of identifying individual emitters via unique characteristics of different emitters. In this paper, we consider a SEI problem with transmitter changing modulations scenario. There have been few previous studies on this type of scenario. To cope with the daunting challenge, a variable-modulation SEI framework with domain adaptation is proposed. The components characteristics of transmitter are analyzed and the distortion models are established for simulation dataset generation. The received in-phase/quadrature (I/Q) signals are demodulated and reconstructed to obtain baseband ideal modulation signals. The received signals and the ideal modulation signals corresponding to demodulation and reconstruction are merged and embedded into the feature extraction network. Domain adversarial neural network (DANN) is added into the SEI framework to generate domain-invariant fingerprint features, thus realizing variable-modulation SEI. To better align the distortion features of emitters with variable modulations, Gaussian Encoder is designed to project fingerprint features into Gaussian distribution space. Numerous experiments show that the proposed SEI framework can improve recognition accuracy of individual emitter for single modulation and variable transfer greatly, and outperform the existing transfer learning methods. The ablation study demonstrates the components of framework are complementary. The complexity of framework is acceptable and it can extend to large-scale use. The robustness of framework is verified through modulation transfer among PSK and QAM.

Direct sequence spread spectrum (DSSS) signals are widely used in various military and civilian communication systems owing to its useful properties, such as lower working signal‐to‐noise ratio, strong anti‐jamming capability, and robustness to multi‐path fading. In past few years, the estimation for spreading sequence in non‐cooperative context has attracted lots of attention. Several methods are developed to realise a recovery of the sequence. Eigenvalue decomposition (EVD) is a classical method to obtain an effective estimation by extracting the main eigenvectors. The only obstacle to apply EVD method into practical systems is high complexity of computation when spreading sequence is long. Alternative algorithms such as neural network and clustering method have lower complexity, but an evident loss in performance. In this work, the authors propose to generalise the EVD algorithm to intermediate frequency (IF) short‐code DSSS with an unknown carrier offset. The blind despreading process is designed to complete correlation demodulation. As a result, the computational afford is largely decreased due to the operation on IF real signal. To evaluate the performance, they derive the Crammer‐Rao bound for spreading code estimation and compare the performance of several methods. Simulation demonstrates the superiority of the proposed method in estimation accuracy and runtime.

In the available Jpeg steganography methods, model-based (MB) steganography technique is more secure than Jsteg, F5 and OutGuess. In this paper, we consider the problem of estimating the embedded length of secret messages of MB steganography. We provide an expected distribution of the non-zero AC coefficients' high precision histogram to fit the stegotexts', and adopt the cropped and recompressed calibration to obtain the carrier image approximation. Then, we present a new algorithm to estimate the embedding rates based on least square method. The attacks towards MB are successful with experimental evidence on 2700 carrier images and the stego images of different quality factor and different embedding rates.