Using risky text prompts, such as pornography and violent prompts, to test the safety of text-to-image (T2I) models is a critical task. However, existing risky prompt datasets are limited in three key areas: 1) limited risky categories, 2) coarse-grained annotation, and 3) low effectiveness. To address these limitations, we introduce T2I-RiskyPrompt, a comprehensive benchmark designed for evaluating safety-related tasks in T2I models. Specifically, we first develop a hierarchical risk taxonomy, which consists of 6 primary categories and 14 fine-grained subcategories. Building upon this taxonomy, we construct a pipeline to collect and annotate risky prompts. Finally, we obtain 6,432 effective risky prompts, where each prompt is annotated with both hierarchical category labels and detailed risk reasons. Moreover, to facilitate the evaluation, we propose a reason-driven risky image detection method that explicitly aligns the MLLM with safety annotations. Based on T2I-RiskyPrompt, we conduct a comprehensive evaluation of eight T2I models, nine defense methods, five safety filters, and five attack strategies, offering nine key insights into the strengths and limitations of T2I model safety. Finally, we discuss potential applications of T2I-RiskyPrompt across various research fields.

Image Aesthetic Assessment (IAA) aims to rate the aesthetic quality of images and has many practical applications. However, existing methods typically rely on limited annotated data for training, leading to two key issues: 1) score-only predictions lack interpretability, making it hard for users to understand the reasoning behind ratings; 2) the assessment ability learned through supervised training struggles to generalize to scenarios beyond the training data. To address these challenges, we leverage Multi-Modal Large Language Models (MLLMs) for interpretable image aesthetic assessment. Drawing inspiration from the human aesthetic perception process, we propose two key components: aesthetic attribute assessment (AAA) and scene-aware in-context learning (ICL). AAA is to provide detailed attribute-based analysis by prompting with evaluation criteria. Meanwhile, scene-aware ICL is to improve the model’s understanding of the aesthetic scoring principles across different scenes with given corresponding references. The output of these two components is used to guide the model to provide ratings and interpretations for more reliable and understandable results. Experiments across multiple datasets show the effectiveness of our framework in enhancing MLLM’s aesthetic perception ability and underscore its potential for interpretable IAA.

MOTIVATION: Crohn's disease (CD) exhibits substantial variability in response to biological therapies such as ustekinumab (UST), a monoclonal antibody targeting interleukin-12/23. However, predicting individual treatment responses remains difficult due to the lack of reliable histopathological biomarkers and the morphological complexity of tissue. While recent deep learning methods have leveraged whole-slide images (WSIs), most lack effective mechanisms for selecting relevant regions and integrating patch-level evidence into robust patient-level predictions. Therefore, a framework that captures local histological cues and global tissue context is needed to improve prediction performance. RESULTS: We propose a novel clustering-enhanced weakly supervised learning framework to predict UST treatment response from pre-treatment WSIs of CD patients. First, patches from WSIs were encoded using a pre-trained vision foundation model, and k-means clustering was applied to identify representative morphological patterns. Discriminative patches associated with treatment outcomes were selected via a DenseNet-based classifier, with Grad-CAM used to enhance interpretability. To aggregate patch-level predictions, we adopted a multi-instance learning approach, from which whole-slide features were extracted using both patch likelihood histograms and bag-of-words representations. These features were subsequently used to train a classifier for final response prediction. Experimental results on an independent test set demonstrated that our WSI-level model achieved superior predictive performance with an AUC of 0.938 (95% CI: 0.879-0.996), sensitivity of 0.951, and specificity of 0.825, outperforming baseline patch-level models. These findings suggest that our method enables accurate, interpretable, and scalable prediction of biological therapy response in CD, potentially supporting personalized treatment strategies in clinical settings. AVAILABILITY AND IMPLEMENTATION: https://github.com/caicai2526/USTAIM.

Abstract Although existing image-text retrieval methods show strong retrieval performance, they generally fail to explicitly model the subtle semantic difference within categories. To address this problem, we propose a new image-text retrieval method, called CLIP-based Semantic Refinement Method For Image-Text Retrieval (CLIP2SRITR). The proposed method consists of a modal alignment part and a semantic matching part, where the former is to learn better alignment between two modalities and the latter is to enhance the aggregation of image-text features intra-class. The pipeline helps model the distinction between image-text pairs with semantic information differences. In addition, CLIP2SRITR leverages additive angular margin for image-text retrieval loss function to maximize classification boundaries, achieving the goal of increasing intra-class similarity and inter-class variability. Through extensive experiments on three image-text benchmarks, e.g. Wikipedia, Pascal-Sentence, and NUS-WIDE, we show that CLIP2SRITR outperforms state-of-the-art methods, verifying the effectiveness of our method.

In recent years, 3D models have been utilized in many applications, such as auto-drivers, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models efficiently from textual descriptions is a promising but challenging way to solve this problem. In this paper, inspired by the creative mechanisms of human imagination, which concretely supplement the target model from ambiguous descriptions built upon human experiential knowledge, we propose a novel text-3D generation model (T2TD). T2TD aims to generate the target model based on the textual description with the aid of experiential knowledge. Its target creation process simulates the imaginative mechanisms of human beings. In this process, we first introduce the text-3D knowledge graph to preserve the relationship between 3D models and textual semantic information, which provides related shapes like humans' experiential information. Second, we propose an effective causal inference model to select useful feature information from these related shapes, which can remove the unrelated structure information and only retain solely the feature information strongly related to the textual description. Third, we adopt a novel multi-layer transformer structure to progressively fuse this strongly related structure information and textual information, compensating for the lack of structural information, and enhancing the final performance of the 3D generation model. The final experimental results demonstrate that our approach significantly improves 3D model generation quality and outperforms the SOTA methods on the text2shape datasets.

With the emergence of edge computing, there is a growing need for advanced technologies capable of real-time, efficient processing of complex data on edge devices, particularly in mobile health systems handling pathological images. On edge computing devices, the lightweighting of models and reduction of computational requirements not only save resources but also increase inference speed. Although many lightweight models and methods have been proposed in recent years, they still face many common challenges. This article introduces a novel convolution operation, Dynamic Scalable Convolution (DSC), which optimizes computational resources and accelerates inference on edge computing devices. DSC is shown to outperform traditional convolution methods in terms of parameter efficiency, computational speed, and overall performance, through comparative analyses in computer vision tasks like image classification and semantic segmentation. Experimental results demonstrate the significant potential of DSC in enhancing deep neural networks, particularly for edge computing applications in smart devices and remote healthcare, where it addresses the challenge of limited resources by reducing computational demands and improving inference speed. By integrating advanced convolution technology and edge computing applications, DSC offers a promising approach to support the rapidly developing mobile health field, especially in enhancing remote healthcare delivery through mobile multimedia communication.

Recently, advancements in text-to-image synthesis and image customization have drawn significant attention. Among these technologies, foreground-driven image synthesis models aim to create diverse scenes for specific foregrounds, showing broad application prospects. However, existing foreground-driven diffusion models struggle to accurately generate scenes with layouts that align with user intentions. To address these challenges, we propose CompCraft, a training-free framework that enhances layout control and improves overall generation quality in current models. First, CompCraft identifies that the failure of existing methods to achieve effective control arises from the excessive influence of fully denoised foreground information on the generated scene. To address this, we propose a foreground regularization strategy that modifies the foreground-related attention maps, reducing their impact and ensuring better integration of the foreground with the generated scene. Then, we propose a series of inference-time layout guidance strategies to guide the image generation process with the user’s finely customized layouts. These strategies enable current foreground-driven diffusion models with accurate layout control. Finally, we introduce a comprehensive benchmark to evaluate CompCraft. Both quantitative and qualitative results demonstrate that CompCraft can effectively generate high-quality images with precise customized layouts, showcasing its strong capabilities in pratical image synthesis applications.

Recent advancements in text-to-image technology have significantly advanced the field of image customization. Among various applications, the task of customizing diverse scenes for user-specified composited elements holds great application value but has not been extensively explored. Addressing this gap, we propose AnyScene, a specialized framework designed to create varied scenes from compos-ited foreground using textual prompts. AnyScene addresses the primary challenges inherent in existing methods, particularly scene disharmony due to a lack of foreground semantic understanding and distortion of foreground elements. Specifically, we develop a foreground injection module that guides a pretrained diffusion model to generate cohesive scenes in visual harmony with the provided foreground. To enhance robust generation, we implement a layout control strategy that prevents distortions of foreground elements. Furthermore, an efficient image blending mechanism seam-lessly reintegrates foreground details into the generated scenes, producing outputs with overall visual harmony and precise foreground details. In addition, we propose a new benchmark and a series of quantitative metrics to evaluate this proposed image customization task. Extensive experimental results demonstrate the effectiveness of AnyScene, which confirms its potential in various applications.

The advent of the Internet of Medical Things (IoMT) has greatly fastened the digitization of current medical institutions. Mobile crowdsourcing is an effective strategy for health data collection in IoMT environments to overcome the data-scarce problem. However, due to the openness of IoMT networks, users’ identities and sensitive data may be leaked during IoMT crowdsourcing. Meanwhile, IoMT crowdsourcing may introduce low-quality data from unreliable participants. Multireceiver signcryption is a promising mechanism to ensure confidentiality and authenticity in an efficient manner. However, existing multireceiver signcryptions cannot fully meet the needs of IoMT crowdsourcing in terms of privacy protection, on-demand participation, and malicious behavior resistance. In this article, we integrate attribute-based credentials with multireceiver encryption and propose a novel multireceiver conditional anonymous signcryption (MCAS) scheme for crowdsourced IoMT environments to address the above challenge. Specifically, conditional anonymous authentication with selective attribute disclosure is achieved, thereby allowing a worker to self-disclose some attributes and anonymously certify his/her crowdsourcing qualifications, and also achieving the traceability of malicious behaviors. Meanwhile, one-to-many secure data sharing with outsourced data signcryption and unsigncryption is realized to prevent the leakage of sensitive IoMT data and mitigate the computational burden of power-limited mobile devices. Moreover, rigorous security analysis demonstrates that our MCAS scheme achieves the expected properties, i.e., confidentiality, anonymity, fine-grained authentication, traceability, and nonrepudiation. Extensive experimental results show that our MCAS outperforms state-of-the-art schemes, demonstrating our scheme’s appropriateness for IoMT crowdsourcing.

In this paper, we propose a novel Multi-keyword Fuzzy Symmetric Searchable Encryption (SSE) with patterns hidden, namely MFSSE. In MFSSE, the search trapdoor can be modified differently each time even if the keywords are the same when performing multi-keyword search to prevent the leakage of search patterns. Moreover, MFSSE modifies the search trapdoor by introducing random false negative and false positive errors to resist access pattern leakage. Furthermore, MFSSE utilizes efficient cryptographic algorithms (e.g., Locality-Sensitive Hashing) and lightweight operations (such as, integer addition, matrix multiplication, etc.) to minimize computational and communication, and storage overheads on mobile devices while meeting security and functional requirements. Specifically, its query process requires only a single round of communication, in which, the communication cost is linearly related to the number of the documents in the database, and is independent of the total number of keywords and the number of queried keywords; its computational complexity for matching a document is$O(1)$; and it requires only a small amount of fixed local storage (i.e., secret key) to be suitable for mobile scenarios. The experimental results demonstrate that MFSSE can prevent the leakage of access patterns and search patterns, while keeping a low communication and computation overheads.

In a blockchain-based data trading platform, data users can purchase data sets and computing power through encrypted smart contracts. The security of smart contracts is important as it relates to that of the data platform. However, due to the inability to apply to detection rules with complex structures and the inefficiency of detection, existing malicious code detection methods are not suitable for the encrypted smart contracts in blockchain-based data trading platforms with high transaction rate requirements. In this paper, a practical and privacy-preserving malicious code detection method is proposed for encrypted smart contract in blockchain-based data trading platform. Specifically, we design two kinds of miners to act as the malicious rule processor and the detector respectively for inspecting the encrypted smart contract. The rule processor generates an obfuscated map with the original open-source malicious rule set. The detector performs a malicious inspection algorithm by inputting the obfuscated map and the randomized tokens, where the latter is generated from smart contract. Then, we theoretically analyze the security syntax of the proposed method. The analysis results demonstrate the proposed scheme can achieve$\mathcal {L}$-secure against adaptive attacks. Extensive experiments are carried out through the open-source real rule sets, which show that the proposed scheme can reduce communication time and communication overhead.

Encrypted behavior identification is crucial in ensuring network security. Most existing solutions in this area recognize behavior by observing encrypted traffic patterns between users and applications. However, such solutions rely on features such as timing, packet sequence, and packet length, which may be affected by network fluctuations, and thus have weak generalization capabilities. In this paper, we first analyze the impact of noise on the network, such as parameters and network delays during API requests. By combining a noise-based traffic collector with an improved Transformer model, we propose a system-level denoising Transformer method for encrypted traffic behavior identification called SD-Transformer. It is able to filter system noise by utilizing an attention mechanism and targeted noise packet masking. We evaluate the performance of SD-Transformer on three datasets, i.e., ISCX-VPN, USTC-TFC, and our generated noise-containing Web Application Traffic dataset (WEB-APP), and it achieves an accuracy of 95.97%, 93.59%, and 99.82%, respectively. Besides, compared to the state-of-the-art methods, the accuracy is increased to 96.82% (↑16.0%) and 85.41% (↑17.76%) on the WEB-APP dataset under different API parameters and network latency environments, respectively. Additionally, the target mask of the SD-Transformer achieves 96.45% accuracy with an improvement of 11.29% on the WEB-APP dataset with latency.

Private individual information are increasingly exposed through high-dimensional and high-order data, with the wide deployment of learning techniques. These data are typically expressed in form of tensors, but there is no principled way to guarantee privacy for tensor-valued queries. Conventional differential privacy is typically applied to scalar values without a precise definition on the shape of the queried data. Realizing that the conventional mechanisms do not take the data structural information into account, we proposeTensor Variate Gaussian(TVG), a new$(\epsilon,\delta) $-differential privacy mechanism for tensor-valued queries. We further introduce two mechanisms based on TVG with an improved utility by imposing the unimodal differentially-private noise. With the utility space available, the proposed mechanisms can be instantiated with an optimized utility, and the optimization problem has a closed-form solution scalable to large-scale problems. Finally, we experimentally test our mechanisms on a variety of datasets and models, demonstrating that TVG is superior than other state-of-the-art mechanisms on tensor-valued queries.

APT malware exploits HTTP to establish communication with a C & C server to hide their malicious activities. Thus, HTTP-based APT malware infection can be discovered by analyzing HTTP traffic. Recent methods have been dependent on the extraction of statistical features from HTTP traffic, which is suitable for machine learning. However, the features they extract from the limited HTTP-based APT malware traffic dataset are too simple to detect APT malware with strong randomness insufficiently. In this paper, we propose an innovative approach which could uncover APT malware traffic related to data exfiltration and other suspect APT activities by analyzing the header fields of HTTP traffic. We use the Referer field in the HTTP header to construct a web request graph. Then, we optimize the web request graph by combining URL similarity and redirect reconstruction. We also use a normal uncorrelated request filter to filter the remaining unrelated legitimate requests. We have evaluated the proposed method using 1.48 GB normal HTTP flow from clickminer and 280 MB APT malware HTTP flow from Stratosphere Lab, Contagiodump, and pcapanalysis. The experimental results have shown that the URL-correlation-based APT malware traffic detection method can correctly detect 96.08% APT malware traffic, and its recall rate is 98.87%. We have also conducted experiments to compare our approach against Jiang’s method, MalHunter, and BotDet, and the experimental results have confirmed that our detection approach has a better performance, the accuracy of which reached 96.08% and the F1 value increased by more than 5%.

With the evolution of traditional civil aviation into "e-enabled" aviation, automatic dependent surveillance-broadcast (ADS-B) system plays an important role to replace radar to become the cornerstone of the next generation air traffic management. However, ADS-B system is a broadcast-type data link and ADS-B signals are unauthenticated, thus inserting a false aircraft into the ADS-B system is easy. In this paper, to filter spoofed targets, we present ADS-B data authentication scheme based on AH protocol. Security analysis demonstrates that the proposed scheme can achieve integrity of ADS-B messages, authenticity of data origin sources and resistance against replay attacks.