
Image privacy protection relies on effective diffusion, yet existing methods still suffer from limited cross-plane interaction and insufficient perturbation propagation. To address this issue, this paper proposes a chaotic image privacy protection method based on Layer-Coupled Co-Evolutionary Cellular Automata (LCCE-CA). A diffusion-oriented Life-like CA rule optimization method is first designed by imposing finite-step balance and temporal-correlation constraints to obtain low-correlation and near-balanced diffusion rules. Then, a reversible LCCE-CA mechanism is constructed by coupling image bit-planes with auxiliary co-evolution planes, enabling explicit cross-plane feedback at each iteration. Based on this mechanism, a chaotic image privacy protection framework is developed and validated on standard grayscale image encryption experiments. Compared with the traditional 8th-order reversible CA, LCCE-CA reduces the early-stage mean balance deviation from 0.3003 to 0.0008, corresponding to a 99.7% reduction. At the 8th iteration, the cumulative perturbation propagation ratio increases from 0.2580 to 0.5609. Experiments on nine standard grayscale images with sizes of 256 & times; 256 and 512 & times; 512 show noise-like protected images, nearly uniform histograms, and strong spatial decorrelation, with a maximum absolute adjacent-pixel correlation coefficient of 0.00857. The scheme exhibits strong plaintext and ciphertext sensitivity, with the average Number of Pixels Change Rate (NPCR) and Unified Average Changing Intensity (UACI) for plaintext sensitivity reaching 99.6075% and 33.4708%, respectively. These results indicate that LCCE-CA provides a practical reversible diffusion framework for secure image privacy protection.
As the Segment Anything Model (SAM) becomes a popular foundation model in computer vision, its adversarial robustness has become a concern that cannot be ignored. This work investigates whether it is possible to attack SAM with image-agnostic Universal Adversarial Perturbation (UAP). In other words, we seek a single perturbation that can fool the SAM to predict invalid masks for most (if not all) images. We demonstrate conventional image-centric attack framework is effective for image-dependent attacks but fails for universal adversarial attacks. To this end, we propose a perturbation-centric framework for UAP generation on SAM, which shifts the optimization focus from image-specific clean and adversarial image pairs to the UAP itself. Based on this framework, we develop a contrastive learning method in which the UAP is treated as the anchor sample to be optimized, its augmented version is used as the positive sample, and natural images are used as negatives. The effectiveness of our proposed perturbation-centric UAP generation method is validated by both quantitative and qualitative results. On top of the ablation study to understand various components in our proposed method, we shed light on the roles of positive and negative samples in making the generated UAP effective for attacking SAM.
Federated Learning (FL) enables collaborative model training without centralizing raw data and has become an important paradigm for privacy-sensitive intelligent systems. Nevertheless, its distributed architecture, heterogeneous data, and unreliable participants introduce substantial robustness and security challenges, ranging from communication noise and system failures to poisoning, privacy inference, and Byzantine attacks. In this paper, we present a structured survey of robust federated learning. We first organize the literature through a threat-oriented taxonomy that covers poisoning attacks, privacy leakage risks, Byzantine behavior, and scenario-specific robustness challenges. We explicitly analyze stronger adversaries that collude, coordinate poisoning campaigns, replace models behind secure aggregation, and adapt their optimization to defense-specific weaknesses. We then review representative defense mechanisms, including robust aggregation, backdoor defense, privacy-preserving training, secure aggregation, and personalized robustness enhancement. Particular attention is given to three recurring tensions in the literature: robustness under Non-IID data, robustness-efficiency trade-offs, and robustness-privacy trade-offs. We further discuss robust federated learning in wireless and IoT environments, where communication uncertainty and resource constraints become first-order concerns. We examine how existing robustness mechanisms translate, or fail to translate, to foundation-model-based FL, federated fine-tuning of large language models, federated reinforcement learning, agentic federated systems, and federated retrieval-augmented generation. Finally, we summarize open challenges and outline future research directions for building more reliable, efficient, and deployable federated learning systems.
The integration of multifunctional modules into ultrathin, spatially constrained flexible electronics often leads to localized heat accumulation, challenging device reliability under conformal operation. Achieving precise heatflux manipulation, mechanical flexibility, and scalable fabrication within a unified platform remains an open challenge. Here, we report a gradient-discretized design strategy for flexible thermal metamaterials that combines multiscale topology optimization with transformation thermotics. This framework links microstructural geometry, deformation-induced effects, and macroscopic thermal functionality, including thermal cloaking and thermal concentration. Using flexible printed-circuit fabrication, we fabricate gradient arrays containing 6 & times; 6 to 20 & times; 20 unit cells, with pitches ranging from 10 to 3 mm, within a fixed 60 & times; 60 mm2 footprint. We also develop a coupled thermomechanical resistance model to quantify bending-induced perturbations. In the flat state, the thermal-cloaking function suppresses the temperature gradient within the protected region to approximately 1% of the surrounding background gradient, thereby enabling thermal concealment of embedded heterogeneous structures. The thermal-concentration function enhances local heat focusing by nearly one order of magnitude, increasing the temperature difference available to a thermoelectric module. Both functions remain effective under bending at a radius of 19 mm, with only moderate performance degradation. These results establish a scalable and mechanically compliant platform for programmable heat-flux control in next-generation conformal and wearable electronics.
While the orthographic expectation effect (OEE) is well-documented in alphabetic languages, its manifestation in logographic systems like Chinese, particularly among children with atypical auditory experience such as those with cochlear implants (CIs), remains unexplored. This study investigated whether Mandarin-speaking children can form orthographic expectations for Chinese characters through auditory exposure alone, comparing 36 prelingually deaf children with CIs and 36 age-matched children with normal hearing (NH). Using a novel-word learning paradigm, participants were auditorily exposed to pseudo-characters. Their reaction times in a subsequent lexical decision task were analyzed using Generalized Linear Mixed-Effects Models (GLMM) to compare auditorily learned versus unlearned phonograms and non-phonograms, as well as predictable versus unpredictable phonetic radicals. Results revealed that both groups exhibited significantly faster reaction times for auditorily learned phonograms, and this expectation effect emerged robustly only when the phonetic radicals were highly predictable. However, children with CIs demonstrated markedly slower responses than their NH peers across all conditions. These findings demonstrate that Mandarin-speaking children can form robust orthographic expectations through auditory input regardless of hearing status. Although children with CIs exhibit slower baseline processing speeds due to underlying perceptual constraints, the magnitude of their orthographic expectation effect remains remarkably intact and comparable to their normal-hearing peers. Ultimately, this highlights the resilient nature of cross-modal reading acquisition, offering crucial neurocognitive insights for designing adaptive literacy interventions in clinical and educational settings.