Text-guided image inpainting aims to inpaint masked image regions based on a textual prompt while preserving the background. Although diffusion-based methods have become dominant, their property of modeling the entire image in latent space makes it challenging for the results to align well with prompt details and maintain a consistent background. To address these issues, we explore Mask AutoRegressive (MAR) models for this task. MAR naturally supports image inpainting by generating latent tokens corresponding to mask regions, enabling better local controllability without altering the background. However, directly applying MAR to this task makes the inpainting content either ignore the prompts or be disharmonious with the background context. Through analysis of the attention maps from the inpainting images, we identify the impact of background tokens on text tokens during the MAR generation, and leverage this to designToken Painter, a training-free text-guided image inpainting method based on MAR. Our approach introduces two key components: (1) Dual-Stream Encoder Information Fusion (DEIF), which fuses the semantic and context information from text and background in frequency domain to produce novel guidance tokens, allowing MAR to generate text-faithful inpainting content while keeping harmonious with background context. (2) Adaptive Decoder Attention Score Enhancing (ADAE), which adaptively enhances attention scores on guidance tokens and inpainting tokens to further enhance the alignment of prompt details and the content visual quality. Extensive experiments demonstrate that our training-free method outperforms prior state-of-the-art methods across almost all metrics.

Mainstream research in audio-visual learning has focused on designing task-specific expert models, primarily implemented through sophisticated multimodal fusion approaches. Recently, a few efforts have aimed to develop more task-independent or universal audiovisual embedding networks, encoding advanced representations for use in various audiovisual downstream tasks. This is typically achieved by fine-tuning large pretrained transformers, such as Swin-V2-L and HTS-AT, in a parameter-efficient manner through techniques such as tuning only a few adapter layers inserted into the pretrained transformer backbone. Although these methods are parameter-efficient, they suffer from significant training memory consumption due to gradient backpropagation through the deep transformer backbones, which limits accessibility for researchers with constrained computational resources. In this paper, we present Meta-Token Learning (Mettle), a simple and memory-efficient method for adapting large-scale pretrained transformer models to downstream audio-visual tasks. Instead of sequentially modifying the output feature distribution of the transformer backbone, Mettle utilizes a lightweight Layer-Centric Distillation (LCD) module to distill in parallel the intact audio or visual features embedded by each transformer layer into compact meta-tokens. This distillation process considers both pretrained knowledge preservation and task-specific adaptation. The obtained meta-tokens can be directly applied to classification tasks, such as audio-visual event localization and audio-visual video parsing. To further support fine-grained segmentation tasks, such as audio-visual segmentation, we introduce a Meta-Token Injection (MTI) module, which utilizes the audio and visual meta-tokens distilled from the top transformer layer to guide feature adaptation in earlier layers. Extensive experiments on multiple audiovisual benchmarks demonstrate that our method significantly reduces memory usage and training time while maintaining parameter efficiency and competitive accuracy.

To enhance shares visual quality and security, meaningful secret image sharing relies on pre-input cover images to endow shadow images with interpretable semantics. However, the recently proposed schemes often yield shadows with mediocre visual quality and compromised security, such as vulnerability to statistical analysis or information leakage. Generative SIS (GSIS) introduces image generation or other operations, either to generate high-quality shadows or to eliminate the need for pre-input covers. Our prior \((2,2)\) -GSIS generated meaningful shares without covers but incurred non-critical leakage and did not support lossless reconstruction. Grayscale image colorization, being a widely adopted image processing operation, offers a promising route for GSIS by enriching semantics through chrominance synthesis. We introduce a colorization-driven GSIS. Chrominance components are shared via a \((k,n)\) -threshold SIS. Near-neutral chrominance from color templates provides structural priors that guide the synthesis of share pixels. The generated chrominance supersedes the template values and directly participates in colorization. This dynamic constraint departs from the linear modification paradigm of cover-based schemes, yielding shares that are visually natural and semantically preserved, without information leakage, and enabling lossless recovery from any \( k \) of \( n \) shares. Theoretical analysis and experiments validate the effectiveness and advantages of the framework.

In the business scenarios at Ant Group, there is a rising demand for collaborative data analysis among multiple institutions, which can promote health insurance, financial services, risk control, and others. However, the increasing concern about privacy issues has led to data silos. Secure Multi-Party Computation (MPC) provides an effective solution for collaborative data analysis, which can utilize data value while ensuring data security. Nevertheless, the performance bottlenecks of MPC and the strong demand for scalability pose great challenges to secure collaborative data analysis frameworks. In this paper, we build a secure collaborative data analysis system SCQL with a general purpose. We design more efficient MPC protocols and relational operators to meet the demand for scalability. In terms of system design, we aim to implement a system with security, usability, and efficiency. We conduct extensive experiments on SCQL to validate our optimization improvements: (1) Our optimized secure sort protocol sorts one million 64-bit data in only 4.5 minutes, 126× faster than EMP (9.4 hours). (2) The end-to-end execution time of the typical vertical scenario query is reduced by 1991× from the state-of-the-art semi-honest collaborative analysis framework Secrecy (rewritten with Additive Secret Sharing protocol), with appropriate security tradeoffs. (3) We test the system in the WAN setting with input size = 10 7 to demonstrate the scalability. We have successfully deployed SCQL to address problems in real-world business scenarios at Ant Group.

Abstract Secret image sharing (SIS) is an important method to protect the security of secret images. When part of the shadows generated by the secret sharing is leaked or when the secret image is restored, the shadows and the secret need to be renewed. Aiming at secret image and shadow image renewal, a scheme for renewing secret image and shadow images is proposed. The scheme is to multiply the original and renewed shadow of the corresponding serial number to get a new shadow over finite fields. Our scheme can realise the renewal of the secret image and shadows and has characteristics of the variable threshold, secure public transmission, variable size, and lossless recovery. This paper theoretically analyses and proves the security of the proposed scheme and verifies the effectiveness through a large number of experiments.

In some particular situations, participants need to recover different secrets both within a group (i.e., intragroup) and between two groups (i.e., intergroup). However, most of the existing multilevel secret sharing (MLSS) and multigroup secret sharing (MGSS) schemes mainly focus on how to protect a secret between one or more groups. In this paper, we propose a polynomial-based scheme to share multiple secret images both within a group and between groups. The random elements’ utilization model of integer linear programming is used to find polynomial coefficients that meet certain conditions so that each participant holds only one shadow image and some of them can recover secrets of both intergroup and intragroup. In addition, our scheme based on polynomials has the advantage of low computational complexity. Theoretical analysis and experiments show that the proposed scheme is feasible and effective.

Shadow images generated from Shamir’s polynomial-based secret image sharing (SSIS) may leak the original secret image information, which causes a significant risk. The occurrence of this risk is closely related to the basis of secret image sharing, Shamir’s polynomial. Shamir’s polynomial plays an essential role in secret sharing, but there are relatively few studies on the power and order number of Shamir’s polynomial. In order to improve the security and effectiveness of SSIS, this paper mainly studies the utility of two parameters in Shamir’s polynomial, order number and power. Through the research of this kind of utility, the choice of order number and power can be given under different security requirements. In this process, an effective shadow image evaluation algorithm is proposed, which can measure the security of shadow images generated by SSIS. The user can understand the influence rule of the order number and power in SSIS, so that the user can choose the appropriate order number and power according to different security needs.