Existing deepfake detectors predominantly process entire facial images as input, which limits their sensitivity to local forgery cues due to representation bias and information loss through CNN feature aggregation. To address these limitations, we propose IDCNet, a novel deepfake detection framework based on image decomposition and cross-view distillation. Our key insight is that decomposing images into complementary views enables specialized processing of global and local forgery cues, while cross-view distillation facilitates their mutual enhancement. Specifically, the framework employs a lightweight U-Net generator with a dual-objective mechanism to decompose input images into global content and local detail views, optimized through reconstruction and classification losses. A cross-view distillation strategy is then applied to enhance complementary feature learning between views. Furthermore, to integrate local artifact information into existing detection models without architectural modifications, we propose a feature alignment method. Extensive experiments across 14 forgery methods demonstrate the effectiveness of our approach, achieving up to 4.4% AUC improvement on the CDFV2 dataset compared to state-of-the-art methods. The source code is available at: https://github.com/wangzhiyuan120/idcnet

Embodied AI systems, integrating Large Vision-Language Models (LVLMs) and Large Language Models (LLMs) with physical actuators and sensors, face unique robustness and security challenges stemming from the complex interplay between perception, cognition, and actuation in real-world environments. This survey provides a systematic analysis of these vulnerabilities and associated attack surfaces. We propose a tripartite vulnerability taxonomy comprising foundational, integration, and contextual risks. Foundational vulnerabilities arise from inherent limitations in current AI architectures and training paradigms; Integration vulnerabilities emerge from the composition of cyber-physical components; And contextual vulnerabilities stem from dynamic physical environments and deployment conditions. Correspondingly, we present a comprehensive attack taxonomy that encompasses foundational attacks on LLMs/LVLMs (including logits-based, optimization-based, prompt-based, and cross-modality attacks), integration-level cybersecurity threats (such as man-in-the-middle, firmware, side-channel, and supply chain attacks), and contextual attacks (primarily sensor spoofing across multiple modalities). We further examine representative failure modes of the cognitive core, review existing evaluation methodologies and benchmarks, and synthesize a multi-layer defense framework that integrates perceptual redundancy, runtime monitoring, and hardware-enforced safety mechanisms. This work offers a unified conceptual framework and practical roadmap for designing and evaluating robust, secure Embodied AI systems in safety-critical real-world deployments.

Novel view synthesis has attracted tremendous research attention recently for its applications in virtual reality and immersive telepresence. Rendering a locally immersive light field (LF) based on arbitrary large baseline RGB references is a challenging problem that lacks efficient solutions with existing novel view synthesis techniques. In this work, we aim at truthfully rendering local immersive novel views/LF images based on large baseline LF captures and a single RGB image in the target view. To fully explore the precious information from source LF captures, we propose a novel occlusion-aware source sampler (OSS) module which efficiently transfers the pixels of source views to the target view’s frustum in an occlusion-aware manner. An attention-based deep visual fusion module is proposed to fuse the revealed occluded background content with a preliminary LF into a final refined LF. The proposed source sampling and fusion mechanism not only helps to provide information for occluded regions from varying observation angles, but also proves to be able to effectively enhance the visual rendering quality. Experimental results show that our proposed method is able to render high-quality LF images/novel views with sparse RGB references and outperforms state-of-the-art LF rendering and novel view synthesis methods.

Image-based geometric modeling and novel view synthesis based on sparse large-baseline samplings are challenging but important tasks for emerging multimedia applications such as virtual reality and immersive telepresence. Existing methods fail to produce satisfactory results due to the limitation on inferring reliable depth information over such challenging reference conditions. With the popularization of commercial light field (LF) cameras, capturing LF images (LFIs) is as convenient as taking regular photos, and geometry information can be reliably inferred. This inspires us to use a sparse set of LF captures to render high-quality novel views globally. However, the fusion of LF captures from multiple angles is challenging due to the scale inconsistency caused by various capture settings. To overcome this challenge, we propose a novel scale-consistent volume rescaling algorithm that robustly aligns the disparity probability volumes (DPV) among different captures for scale-consistent global geometry fusion. Based on the fused DPV projected to the target camera frustum, novel learning-based modules (i.e., the attention-guided multi-scale residual fusion module, and the disparity field-guided deep re-regularization module), which comprehensively regularize noisy observations from heterogeneous captures for high-quality rendering of novel LFIs, have been proposed. Both quantitative and qualitative experiments over the Stanford Lytro Multi-view LF dataset show that the proposed method outperforms state-of-the-art methods significantly under different experiment settings for disparity inference and LF synthesis.

Text-to-image diffusion models are capable of producing high-quality images from textual descriptions; however, they present notable security concerns. These include the potential for generating Not-Safe-For-Work (NSFW) content, replicating artists’ styles without authorization, or creating deepfakes. Recent advancements have proposed concept erasure techniques to eliminate sensitive concepts from these models, aiming to mitigate the generation of undesirable content. Nevertheless, the robustness of these techniques against a wide range of adversarial inputs has not been comprehensively investigated. To address this challenge, a novel two-stage optimization attack framework based on adversarial perturbations, referred to as Concept Embedding Adversary (CEA), was proposed in the present study. By leveraging the cross-modal alignment priors of the CLIP model, CEA iteratively adjusts adversarial embedding vectors to approximate the semantic expression of specific target concepts. This process enables the construction of deceptive adversarial prompts that exploit diffusion models, compelling them to regenerate previously erased concepts. The performance of concept erasure methods was evaluated, specifically when dealing with diversified adversarial prompts targeting erased concepts, such as NSFW content, artistic styles, and objects. Extensive experimental results demonstrate that existing concept erasure methods are unable to completely eliminate target concepts. In contrast, the proposed CEA framework exploits residual vulnerabilities within the generative latent space through a two-stage optimization process. By achieving precise cross-modal alignment, CEA attains significantly higher ASR in regenerating erased concepts.