The integration of AI with medical images enables the extraction of implicit image-derived biomarkers for a precise health assessment. Recently, retinal age, a biomarker predicted from fundus images, has become a proven predictor of systemic disease risks, behavioral patterns, aging trajectory and even mortality. However, the capability to infer such sensitive biometric data raises significant privacy risks, where unauthorized use of fundus images could lead to bioinformation leakage, breaching individual privacy. In response, we formulate a new research problem of biometric privacy associated with medical images and propose RetinaGuard, a novel privacy-enhancing framework that employs a feature-level generative adversarial masking mechanism to obscure retinal age while preserving image visual quality and disease diagnostic utility. The framework further utilizes a novel multiple-to-one knowledge distillation strategy incorporating a retinal foundation model and diverse surrogate age encoders to enable a universal defense against black-box age prediction models. Comprehensive evaluations confirm that RetinaGuard successfully obfuscates retinal age prediction with minimal impact on image quality and pathological feature representation. RetinaGuard is also flexible for extension to other medical image-derived biomarkers.

One-shot federated learning (FL) has gained traction due to its communication efficiency and scalability. However, unlike traditional FL, which can frequently align client models through multiple rounds of client training and server aggregation, one-shot FL allows only a single communication round, causing each client to easily overfit its local data and leading to divergent objectives. Without any chance to iteratively correct these biases or mitigate heterogeneity, the aggregated model significantly deviates from the optimum achieved under dataset centralized training. To address this challenge, we propose OFedED, a one-shot FL framework that preserves privacy and fully exploits client data by combining local data distillation with server-side ensemble learning. Each client distills its own dataset into an ultracompact coreset that retains essential distributional characteristics; the server aggregates these coresets to guide ensemble training that captures inter-client heterogeneity, harnesses complementary knowledge, corrects local bias, and drives performance close to centralized training. In addition, we theoretically show that, under mild assumptions for local data distillations, the server can simulate a centralized optimization process by finetuning on the aggregated distilled data, effectively bypassing the need for multiple communication rounds, showing that properly distilled data can encode sufficient task-relevant information to support centralized-level optimization. Extensive experiments reveal that OFedED consistently and significantly outperforms SOTA methods, achieving an improvement of up to 9.17% on MNIST and 3.97% on CIFAR-10, the robustness being verified also by experiments using ResNet and various server-client architectures.

Light Field Focal Stack (LFFS) can be efficiently rendered from a light field (LF) image captured by plenoptic cameras. Differences in the 3D surface and texture of biometric samples are internally reflected in the defocus blur and local patterns between the rendered slices of LFFS. This unique property makes LFFS quite appropriate to differentiate presentation attack instruments (PAIs) from bona fide samples. A patch-based dual-view network (PDVN) is proposed in this paper to leverage the merits of LFFS for face presentation attack detection (PAD). First, original LFFS data are divided into various local patches along spatial dimensions, which distracts the model from learning the useless facial semantics and greatly relieve the problem of insufficient samples. The strategy of dual-view branches is innovatively proposed, wherein the original view and microscopic view can simultaneously contribute to liveness detection. Separable 3D convolution on the focal dimension is verified to be more effective than vanilla 3D convolution for extracting discriminative features from LFFS data. The voting mechanism on predictions of patch LFFS samples further strengthens the robustness of the proposed framework. PDVN is compared with other face PAD methods on IST LLFFSD dataset and achieves perfect performance, i.e., ACER drops to 0.

Attributes skew hinders the current federated learning (FL) frameworks from consistent optimization directions among the clients, which inevitably leads to performance reduction and unstable convergence. The core problems lie in that: 1) Domain-specific attributes, which are non-causal and only locally valid, are indeliberately mixed into global aggregation. 2) The one-stage optimizations of entangled attributes cannot simultaneously satisfy two conflicting objectives, i.e., generalization and personalization. To cope with these, we proposed disentangled federated learning (DFL) to disentangle the domain-specific and cross-invariant attributes into two complementary branches, which are trained by the proposed alternating local-global optimization independently. Importantly, convergence analysis proves that the FL system can be stably converged even if incomplete client models participate in the global aggregation, which greatly expands the application scope of FL. Extensive experiments verify that DFL facilitates FL with higher performance, better interpretability, and faster convergence rate, compared with SOTA FL methods on both manually synthesized and realistic attributes skew datasets.

Since the outbreak of the COVID-19 pandemic, iris recognition has been used increasingly as contactless and unaffected by face masks. Although less user cooperation is an urgent demand for existing systems, corresponding manually annotated databases could hardly be obtained. This paper presents a large-scale database of near-infrared iris images named CASIA-Iris-Degradation Version 1.0 (DV1), which consists of 15 subsets of various degraded images, simulating less cooperative situations such as illumination, off-angle, occlusion, and nonideal eye state. A lot of open-source segmentation and recognition methods are compared comprehensively on the DV1 using multiple evaluations, and the best among them are exploited to conduct ablation studies on each subset. Experimental results show that even the best deep learning frameworks are not robust enough on the database, and further improvements are recommended for challenging factors such as half-open eyes, off-angle, and pupil dilation. Therefore, we publish the DV1 with manual annotations online to promote iris recognition. (http://www.cripacsir.cn/dataset/)