Large-scale vision-language models (e.g., CLIP) have recently achieved remarkable performance in retrieval tasks, yet their potential for Video-based Visible-Infrared Person Re-Identification (VVI-ReID) remains largely unexplored. The primary challenges are narrowing the modality gap and leveraging spatiotemporal information in video sequences. To address the above issues, in this paper, we propose a novel cross-modality feature learning framework named X-ReID for VVI-ReID. Specifically, we first propose a Cross-modality Prototype Collaboration (CPC) to align and integrate features from different modalities, guiding the network to reduce the modality discrepancy. Then, a Multi-granularity Information Interaction (MII) is designed, incorporating short-term interactions from adjacent frames, long-term cross-frame information fusion, and cross-modality feature alignment to enhance temporal modeling and further reduce modality gaps. Finally, by integrating multi-granularity information, a robust sequence-level representation is achieved. Extensive experiments on two large-scale VVI-ReID benchmarks (i.e., HITSZ-VCM and BUPTCampus) demonstrate the superiority of our method over state-of-the-art methods.

The Service Rate Region (SRR) serves as a critical metric for evaluating the concurrent service capacity of distributed storage systems. While several works have characterized the SRR for MDS codes and first order Reed-Muller codes, for high-order Reed-Muller codes the problem becomes way more complicated and only partial results were given by Ly, Soljanin, and Lalitha [IEEE ISIT 2025]. In this paper, we refine the SRR analysis by explicitly characterizing the intersection patterns of recovery sets for high-order Reed-Muller codes, deriving the exact region for the case m=r+1 and providing new types of strictly tighter constraints to bridge the gap between existing approximations and the exact SRR polytope.

Metric Differential Privacy (mDP) extends classical differential privacy (DP) by replacing Hamming adjacency with application-aware distance metrics, which offers utility-preserving protection for structured and continuous data including locations, trajectories, images, and text embeddings. This Systematization of Knowledge (SoK) paper synthesizes a decade of progress (2013-2025), clarifying mDP's foundations and its connections to central and local DP, and surveying three principal mDP mechanism families: homogeneous distance mechanisms, non-homogeneous distance mechanisms, and optimized perturbation mechanisms. We organize applications across geo-location privacy, text and embeddings, image and voice protection, graphs and network telemetry, and federated/edge settings. We also surface open challenges, including robust composition and adversarial modeling, context-adaptive privacy, high-dimensional scalability, and principled geometry-aware trade-off bounds, and distill practical guidance for selecting metrics, mechanisms, and metrics of utility. The goal is a unified reference and roadmap for deploying scalable, utility-preserving metric privacy in real-world systems.

Hardware supply-chain attacks are raising significant security threats to the boot process of multiprocessor systems. In this paper, we investigate critical stages of the multiprocessor system boot process and identify a new, prevalent hardware supply-chain attack surface that can bypass secure boot due to the absence of processor-authentication mechanisms. To defend against such attacks, in this paper, we present PA-Boot, the first formally verified processor-authentication protocol for secure boot in multiprocessor systems. PA-Boot is proved functionally correct and is guaranteed to detect multiple adversarial behaviors, such as processor replacements and man-in-the-middle attacks. The fine-grained formalization of PA-Boot and its fully mechanized security proofs are carried out in the Isabelle/HOL theorem prover with 348 lemmas/theorems and ~7,100 LoC. We further implement in C an instance of PA-Boot. Experiments on the proof-of-concept implementation indicate that PA-Boot can effectively identify boot-process attacks with a minor overhead (4.98% on Linux boot process) and thereby improve the security of multiprocessor systems.

Person Re-IDentification (ReID) aims to identify specific persons from non-overlapping cameras. Recently, some works have suggested using large-scale pre-trained vision-language models like CLIP to boost ReID performance. Unfortunately, existing methods still struggle to address two key issues simultaneously: efficiently transferring the knowledge learned from CLIP and comprehensively extracting the context information from images or videos. To address these issues, we introduce CLIMB-ReID, a pioneering hybrid framework that synergizes the impressive power of CLIP with the remarkable computational efficiency of Mamba. Specifically, we first propose a novel Multi-Memory Collaboration (MMC) strategy to transfer CLIP's knowledge in a parameter-free and prompt-free form. Then, we design a Multi-Temporal Mamba (MTM) to capture multi-granular spatiotemporal information in videos. Finally, with Importance-aware Reorder Mamba (IRM), information from various scales is combined to produce robust sequence features. Extensive experiments show that our proposed method outperforms other state-of-the-art methods on both image and video person ReID benchmarks.

Accurate traffic forecasting is crucial for Intelligent Transportation Systems (ITS) but is significantly challenged by non-periodic external events that disrupt regular traffic patterns. While Graph Neural Networks (GNNs) excel at modeling periodic traffic, they often falter in predicting event-driven dynamics. Existing event-aware methods either rely on manually engineered features with limited generalization or depend on curated textual event datasets that are costly to maintain and incomplete. The advent of Large Language Models (LLMs) offers new avenues for understanding and integrating event information. However, directly applying LLMs for all spatio-temporal reasoning can be inefficient, and effectively leveraging their event understanding capabilities within structured forecasting workflows remains a challenge. This paper introduces FUSE-Traffic, a framework which synergizes the dynamic event querying and understanding prowess of LLMs with the spatio-temporal modeling capabilities of GNNs. FUSE-Traffic features an on-demand event information extraction module using LLM prompting and a cross-attention based multimodal fusion mechanism to integrate rich event semantics with traffic flow features. This design enables the model to dynamically perceive and adapt to event-triggered traffic pattern changes. Comprehensive experiments on the METR-LA and PEMS datasets demonstrate that FUSE-Traffic significantly outperforms state-of-the-art models, especially under high-impact event conditions, showcasing robust predictive accuracy and resilience where traffic patterns are most disrupted. Code available at https://github.com/GeoAICenter/FUSE-Traffic_Sigspatial2025

Cloth-Changing person Re-Identification (CC-ReID) depends significantly on learning discriminative features under the cloth-changing scenario. It is quite challenging due to the large intra-person variance and small inter-person variance caused by clothes changing. To address these issues, in this work we propose a Hierarchical Proxy Learning (HPL) framework to extract clothes-irrelevant and person-invariant features. Specifically, we employ person labels as the main proxy. Instead of leveraging clothing labels as sub proxy, we further propose a clustering-based automatic sub-proxy mining scheme. More specifically, we first construct a person-aware Main Proxy Learning (MPL) to improve the separability of different persons. Then, a Sub Proxy Learning (SPL) is constructed to enhance the intra-person compactness. Finally, a Sub-to-Main Proxy Learning (S2MPL) is proposed to promote the cooperation between the main proxies and sub proxies. In addition, to weed out the negative effect of clothes, we propose a Sample Balance and Diversity (SBD) module, which balances the number of sub proxies in a mini-batch and utilizes semantic guidance to enrich the diversity of clothes, simultaneously. Extensive experiments on two public CC-ReID datasets demonstrate the superiority of our proposed method over most state-of-the-art methods.

As demand grows for efficient, localized processing in edge and in-sensor computing, novel architectural approaches are essential to meet low-power, high-density requirements. Memristor Cellular Nonlinear Networks (M-CNNs) offer a promising path forward, leveraging the unique properties of memristors for adaptable and scalable computation. This paper presents a study of novel M-CNN cell configurations designed to enhance computational versatility and address operational challenges in M-CNN-based systems. By leveraging memristor technology within CNN cells, we propose three distinct configurations: (1) incorporating parallel and series resistive elements for refined control over cell dynamics, (2) introducing a fixed bias voltage to expand computational capabilities, and (3) integrating the Full-Range CNN (FR-CNN) model into M-CNNs for the first time. The proposed topologies are evaluated through dynamic route maps (DRM) and vector field analysis to systematically assess stability and performance across varying design parameters.

Multi-modal image segmentation faces real-world deployment challenges from incomplete/corrupted modalities degrading performance. While existing methods address training-inference modality gaps via specialized per-combination models, they introduce high deployment costs by requiring exhaustive model subsets and model-modality matching. In this work, we propose a unified modality-relax segmentation network (UniMRSeg) through hierarchical self-supervised compensation (HSSC). Our approach hierarchically bridges representation gaps between complete and incomplete modalities across input, feature and output levels. First, we adopt modality reconstruction with the hybrid shuffled-masking augmentation, encouraging the model to learn the intrinsic modality characteristics and generate meaningful representations for missing modalities through cross-modal fusion. Next, modality-invariant contrastive learning implicitly compensates the feature space distance among incomplete-complete modality pairs. Furthermore, the proposed lightweight reverse attention adapter explicitly compensates for the weak perceptual semantics in the frozen encoder. Last, UniMRSeg is fine-tuned under the hybrid consistency constraint to ensure stable prediction under all modality combinations without large performance fluctuations. Without bells and whistles, UniMRSeg significantly outperforms the state-of-the-art methods under diverse missing modality scenarios on MRI-based brain tumor segmentation, RGB-D semantic segmentation, RGB-D/T salient object segmentation. The code will be released at \url{https://github.com/Xiaoqi-Zhao-DLUT/UniMRSeg}.

Large-scale language-image pre-trained models (e.g., CLIP) have shown superior performances on many cross-modal retrieval tasks. However, the problem of transferring the knowledge learned from such models to video-based person re-identification (ReID) has barely been explored. In addition, there is a lack of decent text descriptions in current ReID benchmarks. To address these issues, in this work, we propose a novel one-stage text-free CLIP-based learning framework named TF-CLIP for video-based person ReID. More specifically, we extract the identity-specific sequence feature as the CLIP-Memory to replace the text feature. Meanwhile, we design a Sequence-Specific Prompt (SSP) module to update the CLIP-Memory online. To capture temporal information, we further propose a Temporal Memory Diffusion (TMD) module, which consists of two key components: Temporal Memory Construction (TMC) and Memory Diffusion (MD). Technically, TMC allows the frame-level memories in a sequence to communicate with each other, and to extract temporal information based on the relations within the sequence. MD further diffuses the temporal memories to each token in the original features to obtain more robust sequence features. Extensive experiments demonstrate that our proposed method shows much better results than other state-of-the-art methods on MARS, LS-VID and iLIDS-VID.

Geo-obfuscation is a Location Privacy Protection Mechanism used in location-based services that allows users to report obfuscated locations instead of exact ones. A formal privacy criterion, geoindistinguishability (Geo-Ind), requires real locations to be hard to distinguish from nearby locations (by attackers) based on their obfuscated representations. However, Geo-Ind often fails to consider context, such as road networks and vehicle traffic conditions, making it less effective in protecting the location privacy of vehicles, of which the mobility are heavily influenced by these factors.

Understanding and predicting Origin-Destination (OD) flows is crucial for urban planning and transportation management. Traditional OD prediction models, while effective within single cities, often face limitations when applied across different cities due to varied traffic conditions, urban layouts, and socio-economic factors.

Aiming at the challenges of surveillance video anomaly detection(SVAD),especially the diversity and openness of its event types, we propose CLIP-Augmented Bimodal Memory Enhanced Network for weakly-supervised surveillance video anomaly detection. Specifically, we design a video feature extraction module based on CLIP feature, which significantly improves the ability to capture the semantic content of surveillance videos. Given the problem of semantic diversity of abnormal events, we further design a Bimodal Memory Unit(BMMU), which is used to enhance the model for all types of abnormal events by means of two kinds of memory module, storing the visual features and the textual descriptive features, in order to enhance the model's ability to remember and distinguish various types of anomalous features. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on the UCF-Crime and XD-Violence benchmark datasets.

Occluded person re-identification (ReID) is a very challenging task due to the occlusion disturbance and incomplete target information. Leveraging external cues such as human pose or parsing to locate and align part features has been proven to be very effective in occluded person ReID. Meanwhile, recent Transformer structures have a strong ability of long-range modeling. Considering the above facts, we propose a Teacher-Student Decoder (TSD) framework for occluded person ReID, which utilizes the Transformer decoder with the help of human parsing. More specifically, our proposed TSD consists of a Parsing-aware Teacher Decoder (PTD) and a Standard Student Decoder (SSD). PTD employs human parsing cues to restrict Transformer’s attention and imparts this information to SSD through feature distillation. Thereby, SSD can learn from PTD to aggregate information of body parts automatically. Moreover, a mask generator is designed to provide discriminative regions for better ReID. In addition, existing occluded person ReID benchmarks utilize occluded samples as queries, which will amplify the role of alleviating occlusion interference and underestimate the impact of the feature absence issue. Contrastively, we propose a new benchmark with non-occluded queries, serving as a complement to the existing benchmark. Extensive experiments demonstrate that our proposed method is superior and the new benchmark is essential. The source codes are available at https://github.com/hh23333/TSD.

While deep neural networks provide state-of-the-art solutions to a wide range of programming language tasks, their effectiveness in dealing with foundational program analysis tasks remains under explored. In this paper, we present an empirical study that evaluates four prominent models of code (i.e., CuBERT, CodeBERT, GGNN, and Graph Sandwiches) in two such foundational tasks: (1) alias prediction, in which models predict whether two pointers must alias, may alias or must not alias; and (2) equivalence prediction, in which models predict whether or not two programs are semantically equivalent. At the core of this study is CodeSem, a dataset built upon the source code of real-world flagship software (e.g., Linux Kernel, GCC, MySQL) and manually validated for the two prediction tasks. Results show that all models are accurate in both prediction tasks, especially CuBERT with an accuracy of 89% and 84% in alias prediction and equivalence prediction, respectively. We also conduct a comprehensive, in-depth analysis of the results of all models in both tasks, concluding that deep learning models are generally capable of performing foundational tasks in program analysis even though in specific cases their weaknesses are also evident. Our code and evaluation data are publicly available at https://github.com/CodeSemDataset/CodeSem.

Video-based person Re-Identification (Re-ID) is a hot research topic in intelligent transportation systems, which aims to retrieve video sequences of the same person under non-overlapping surveillance cameras. Compared with static images, video sequences contain more visual information from multiple views, such as spatial and temporal views. However, previous Re-ID methods usually focus on single limited views, lacking diverse observations from different views. To capture richer perceptions and extract more comprehensive representations, we propose a novel learning framework namedTrigeminal Transformers (TMT)to tackle video-based person Re-ID. More specifically, we first design aView-wise Projector (VP)to jointly transform raw videos from spatial, temporal and spatial-temporal views. In addition, inspired by the great success of Vision Transformers (ViT), we introduce the Transformer structure for information enhancement and aggregation. In our work, threeSelf-view Transformers (ST)are proposed to exploit the relationships of local features for information enhancement in spatial, temporal and spatial-temporal. Moreover, aCross-view Transformer (CT)is proposed to aggregate the multi-view features for comprehensive representations. Experimental results indicate that our approach can obtain better performance than some other state-of-the-art approaches on four public Re-ID benchmarks.

Advanced deep convolutional neural networks (CNNs) have shown great success in video-based person re-identification (Re-ID). However, they usually focus on the most obvious regions of persons with a limited global representation ability. Recently, it witnesses that Transformers explore the interpatch relationships with global observations for performance improvements. In this work, we take both the sides and propose a novel spatial-temporal complementary learning framework named deeply coupled convolution-transformer (DCCT) for high-performance video-based person Re-ID. First, we couple CNNs and Transformers to extract two kinds of visual features and experimentally verify their complementarity. Furthermore, in spatial, we propose a complementary content attention (CCA) to take advantages of the coupled structure and guide independent features for spatial complementary learning. In temporal, a hierarchical temporal aggregation (HTA) is proposed to progressively capture the interframe dependencies and encode temporal information. Besides, a gated attention (GA) is used to deliver aggregated temporal information into the CNN and Transformer branches for temporal complementary learning. Finally, we introduce a self-distillation training strategy to transfer the superior spatial-temporal knowledge to backbone networks for higher accuracy and more efficiency. In this way, two kinds of typical features from same videos are integrated mechanically for more informative representations. Extensive experiments on four public Re-ID benchmarks demonstrate that our framework could attain better performances than most state-of-the-art methods.

Virtual Private Cloud (VPC) has become a widely used cloud computing service, serving as a foundational web infrastructure for many organizations. Nevertheless, the growing problem of reachability issues poses significant threats to the security and reliability of VPC networks, potentially resulting in critical security concerns such as data breaches and service outages. Although there has been substantial progress in recent reachability analysis, existing methods lack validation of correctness. Moreover, current analyses are tailored for One-to-One reachability where both the source and the destination are fixed, and fail to efficiently answer One-to-Multi reachability queries, which involve computing all reachable destinations for a given source node. To address the above challenges, we propose VeriReach, the first formally verified algorithm that provides comprehensive and efficient reachability analysis in large-scale VPC networks. The reachability analysis result of VeriReach is proved to be equivalent to the original reachability semantics of the VPC networks, ensuring its correctness (i.e., soundness and completeness). The fine-grained formalization of VeriReach and its fully mechanized correctness proofs are carried out in Isabelle/HOL theorem prover with 282 lemmas/theorems and $\sim 4,900{\mathrm{LoC}}$. We further implement VeriReach in C++ and the evaluations indicate that VeriReach is more efficient and scalable than MonoSAT, the state-of-the-art SMT solver, when applied to large-scale VPC networks for reachability analysis.

Trusted Execution Environments (TEEs) play a crucial role in embedded systems, IoT, and cloud computing. However, their security issues are a major concern, particularly related to defects or improper implementations in access control mechanisms. Such issues can result in severe problems like privilege escalation and unintended memory accesses during inter-domain communication. Moreover, employing mathematical methods for rigorous security guarantees is essential.To address these challenges, we propose Lark, a cross-domain access control for TEEs, which is modeled and verified in Isabelle/HOL. Lark applies orthogonal access control attributes on memory to decouple access permissions of different privilege levels. Additionally, it enforces strict access permission checks for inter-domain communications. For a strict security guarantee, Lark is formalized and verified in Isabelle/HOL, with 84 definitions and 35 lemmas containing ∼1,600 lines of code. The machine-checkable proofs demonstrate that Lark ensures memory isolation and information flow security. We identify and resolve an inter-domain communication issue within an open-source TEE, and develop a prototype that implements the access control features of Lark. Exhaustive evaluations on real-world applications demonstrate that Lark introduces less than 5% performance overhead.

The challenge of requirements for the finer-grained isolated domain in Trusted Execution Environment (TEE) has been increasing, including the accuracy and security of resource management. However, the current access control mechanism for TEE cannot provide strict security assurances due to a lack of strict formal verification. In order to address the problem, in this paper, we first present the definition of multi-domain TEE, and propose a verified tag-based access control framework called REAL to provide the strict access control policy. We develop a high-level formal functional specification of REAL, and prove its correctness and security properties with 119 lemmas/theorems and ∼ 4,000 LOC of Isabelle/HOL. We also implement a page-level access control prototype called SOP-TEE and demonstrate that it correctly achieve the security objectives while merely incurring less than 0.3% overhead.

Video-based person re-identification (Re-ID) aims to automatically retrieve video sequences of the same person under non-overlapping cameras. To achieve this goal, it is the key to fully utilize abundant spatial and temporal cues in videos. Existing methods usually focus on the most conspicuous image regions, thus they may easily miss out fine-grained clues due to the person varieties in image sequences. To address above issues, in this paper, we propose a novel Global-guided Reciprocal Learning (GRL) framework for video-based person Re-ID. Specifically, we first propose a Global-guided Correlation Estimation (GCE) to generate feature correlation maps of local features and global features, which help to localize the high- and low-correlation regions for identifying the same person. After that, the discriminative features are disentangled into high-correlation features and low-correlation features under the guidance of the global representations. Moreover, a novel Temporal Reciprocal Learning (TRL) mechanism is designed to sequentially enhance the high-correlation semantic information and accumulate the low-correlation sub-critical clues. Extensive experiments are conducted on three public benchmarks. The experimental results indicate that our approach can achieve better performance than other state-of-the-art approaches. The code is released at https://github.com/flysnowtiger/GRL.