Advances in talking-head animation based on Latent Diffusion Models (LDM) enable the creation of highly realistic, synchronized videos. These fabricated videos are indistinguishable from real ones, increasing the risk of potential misuse for scams, political manipulation, and misinformation. Hence, addressing these ethical concerns has become a pressing issue in AI security. Recent proactive defense studies focused on countering LDM-based models by adding perturbations to portraits. However, these methods are ineffective at protecting reference portraits from advanced image-to-video animation. The limitations are twofold: 1) they fail to prevent images from being manipulated by audio signals, and 2) diffusion-based purification techniques can effectively eliminate protective perturbations. To address these challenges, we propose Silencer, a two-stage method designed to proactively protect the privacy of portraits. First, a nullifying loss is proposed to ignore audio control in talking-head generation. Second, we apply anti-purification loss in LDM to optimize the inverted latent feature to generate robust perturbations. Extensive experiments demonstrate the effectiveness of Silencer in proactively protecting portrait privacy. We hope this work will raise awareness among the AI security community regarding critical ethical issues related to talking-head generation techniques. Code: https://github.com/yuangan/Silencer.

The reconstruction of dynamic head avatars has gained increasing significance, giving rise to various downstream applications such as visual dubbing and digital human creation. Despite recent advancements, generating novel, unseen expressions for a given identity remains challenging in concurrently achieving (1) accurate expression and consistent appearance and (2) high-quality and realistic faces. This article introduces ExpAvatar, a novel approach crafted to address these challenges. ExpAvatar elaborately leverages the appearance consistency capabilities inherent in 3DMMs-based models along with the robust generalization ability of DDPMs-based models to alleviate appearance drift issues and enhance the generation of unseen expressions. Specifically, ExpAvatar introduces a Face Priors-Conditioned Diffusion (FPDiff) model to inject 3D face priors into generation models through fine-tuning. Furthermore, a Face Priors-Conditioned Catalyst (FPCatalyst) is employed to enhance the inference efficiency and generation quality. Moreover, we propose a unique confidence-based regularizer function to mitigate the effect of imperfect face-tracking estimates, thereby improving the quality of dynamic neural head avatars. Experimental results demonstrate that ExpAvatar surpasses current state-of-the-art solutions in generating unseen expressions, marking an advancement in the realm of dynamic head avatar synthesis. Code: https://github.com/yuangan/ExpAvatar .

Federated Learning (FL) is commonly used to collaboratively train models with privacy preservation. In this paper, we found out that the popular diffusion models have introduced a new vulnerability to FL, which brings serious privacy threats. Despite stringent data management measures, attackers can steal massive private data from local clients through multiple Trojans, which control generative behaviors with multiple triggers. We refer to the new task as ${\bf\textit{DataStealing}}$ and demonstrate that the attacker can achieve the purpose based on our proposed Combinatorial Triggers (ComboTs) in a vanilla FL system. However, advanced distance-based FL defenses are still effective in filtering the malicious update according to the distances between each local update. Hence, we propose an Adaptive Scale Critical Parameters (AdaSCP) attack to circumvent the defenses and seamlessly incorporate malicious updates into the global model. Specifically, AdaSCP evaluates the importance of parameters with the gradients in dominant timesteps of the diffusion model. Subsequently, it adaptively seeks the optimal scale factor and magnifies critical parameter updates before uploading to the server. As a result, the malicious update becomes similar to the benign update, making it difficult for distance-based defenses to identify. Extensive experiments reveal the risk of leaking thousands of images in training diffusion models with FL. Moreover, these experiments demonstrate the effectiveness of AdaSCP in defeating advanced distance-based defenses. We hope this work will attract more attention from the FL community to the critical privacy security issues of Diffusion Models. Code: https://github.com/yuangan/DataStealing.

Audio-driven talking-head synthesis is a popular research topic for virtual human-related applications. However, the inflexibility and inefficiency of existing methods, which necessitate expensive end-to-end training to transfer emotions from guidance videos to talking-head predictions, are significant limitations. In this work, we propose the Emotional Adaptation for Audio-driven Talking-head (EAT) method, which transforms emotion-agnostic talking-head models into emotion-controllable ones in a cost-effective and efficient manner through parameter-efficient adaptations. Our approach utilizes a pretrained emotion-agnostic talking-head transformer and introduces three lightweight adaptations (the Deep Emotional Prompts, Emotional Deformation Network, and Emotional Adaptation Module) from different perspectives to enable precise and realistic emotion controls. Our experiments demonstrate that our approach achieves state-of-the-art performance on widely-used benchmarks, including LRW and MEAD. Additionally, our parameter-efficient adaptations exhibit remarkable generalization ability, even in scenarios where emotional training videos are scarce or nonexistent. Project website: https://yuangan.github.io/eat/

Semantic scene segmentation is vital for a large variety of applications as it enables understanding of 3D data. Nowadays, various approaches based upon point clouds ignore the mathematical distribution of points and treat the points equally. The methods following this direction neglect the imbalance problem of samples that naturally exists in scenes. To avoid these issues, we propose a two-stage semantic scene segmentation framework based on self-attention mechanism and achieved state-of-the-art performance on 3D scene understanding tasks. We split the whole task into two small ones which efficiently relief the sample imbalance issue. In addition, we have designed a new self-attention block which could be inserted into submanifold convolution networks to model the long-range dependencies that exists among points. The proposed network consists of an encoder and a decoder, with the spatial-wise and channel-wise attention modules inserted. The two-stage network shares a U-Net architecture and is an end-to-end trainable framework which could predict the semantic label for the scene point clouds fed into it. Experiments on standard benchmarks of 3D scenes implies that our network could perform at par or better than the existing state-of-the-art methods.

This paper introduces an architecture for segmenting 3D shapes into labeled semantic parts. Our architecture combines viewpoint selection method based on viewpoint entropy, multi-view image-based Fully Convolutional Networks (FCNs) and graph cuts optimization method to yield coherent segmentation of 3D shapes. First, we select iteratively a fixed number of perspectives with the maximum viewpoint entropy from existing viewpoints that can cover the shape's triangles, to maximally and automatically adjust the distance between the viewpoint and the center point of the shape to make sure the shape projected to fill the render window as wide as possible. Second, the image-based FCN is used for efficient view-based reasoning about 3D shape parts. In this process, global features generated by max view pooling are concatenated with every single view's feature in the fully connected layer before upsampling. Then, the multi-view FCN outputs confidence maps per part, which are then input into the projection layer that contains the mapping relationship of every shape's triangles and their projective pixels' positions in the rendered images from selected perspectives. And then, the FCN outputs are projected back onto 3D shape surfaces. and max view pooling is applied to the output of the projection layer so that every triangle of each shape has a unique probability for each label. Finally, graph cuts algorithm is implemented for the final segmentation result.

For a system of distributed processes, correctness can be ensured by (statically) checking whether their composition satisfies properties of interest. However, Web services are distributed processes that dynamically discover properties of other Web services. Since the overall system may not be available statically and since each business process is supposed to be relatively simple, we propose to use runtime monitoring of conversations between partners as a means of checking behavioral correctness of the entire Web service system. Specifically, we identify a subset of UML 2.0 Sequence Diagrams as a property specification language and show that it is sufficiently expressive for capturing safety and liveness properties. By transforming these diagrams to automata, we enable conformance checking of finite execution traces against the specification. We show how our language can be used to specify the Specification Property System (SPS) [1]. We describe an implementation of our approach as part of an industrial system. Finally, we discuss our experience of specifying and monitoring a number of properties from three existing applications.