Jian Li

Transferable adversarial examples (AEs) have attracted considerable attention due to their ability to expose vulnerabilities in black-box deep neural networks (DNNs). However, achieving superior transferability for targeted attacks remains a challenge. In this article, inspired by the observation that AEs with smaller intra-class distances and larger inter-class distances tend to exhibit higher transferability, we propose a novel targeted attack based on Feature Contrastive Optimization (FCO). This attack enhances adversarial transferability by minimizing intra-class distances and maximizing inter-class distances. Specifically, we first define positive samples (belonging to the target class) and negative samples (belonging to non-target classes) that correspond to targeted AEs. Subsequently, leveraging these defined positive and negative samples, we propose two metrics—Intra-class Compactness (IC) and Inter-class Separability (IS)—to construct a novel Feature Contrastive (FC) loss. By integrating this plug-and-play FC loss into standard adversarial objectives, the generated AEs are encouraged to better align with the target class distribution while diverging from those of non-target classes. Extensive experiments on the ImageNet-compatible dataset demonstrate that our approach consistently improves targeted transferability across a broad range of DNN architectures.

We propose a sorting-and-prediction integrated framework for high-capacity reversible data hiding (RDH). The framework constructs a two-dimensional sorting criterion that jointly leverages predicted pixel values and local complexity. A snake-like scanning strategy is then applied to reorganize pixels into a globally smooth embedding domain while maintaining full reversibility. This design suppresses modification propagation in textured regions and stabilizes embedding performance under large payloads. On this basis, a four-layer LPVO-based embedding scheme is developed to further enhance capacity while preserving image fidelity. Experiments are conducted on six standard images and the Kodak dataset. Results show that the proposed method consistently outperforms representative RDH approaches across varying embedding capacities. On the Kodak dataset, the proposed method achieves an average PSNR of 60.43 dB at 20,000 bits, outperforming a recent RL-based RDH method by 0.59 dB. These results validate that constructing a globally smooth embedding domain is an effective strategy for high-fidelity, high-capacity RDH.

Aiming to mitigate image distortion caused by steganography algorithms at high-capacity information embedding and enhance the steganalysis resistance capability of generated stego images, this paper proposes a high-capacity differential steganography algorithm for color images based on multiple adversarial networks. Instead of directly modifying the pixels of the cover image, the algorithm embeds the secret information into the differential plane generated by the two most similar channels of the cover image. Consequently, the distortion of the stego image is minimized while embedding a secret image of the same size. At the same time, the fidelity of the stego and extracted secret images is continually improved through adversarial training between the generator and discriminator in the proposed steganography network. Furthermore, multiple steganalysis networks are parallelly utilized to enhance the steganalysis resistance capability of stego images. In addition, the Lion optimizer is utilized for the first time to improve the convergence speed of the proposed steganographic network. Experimental results show that the comprehensive performance of the proposed algorithm outperforms other state-of-the-art steganography algorithms significantly.