Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains. Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity. To facilitate this approach, we introduce a specialized 11K dataset featuring realistic degradations synthesized across four critical real-world visual processing stages, each annotated with structured chains connecting degradation parameters, perceptual influence, pristine semantic reasoning chain, and conclusion. Comprehensive evaluations demonstrate state-of-theart robustness: Robust-R1 outperforms all general and robust baselines on the real-world degradation benchmark R-Bench, while maintaining superior anti-degradation performance under multi-intensity adversarial degradations on MMMB, MMStar, and RealWorldQA.

Vehicle-to-Everything (V2X) communication faces a critical authentication dilemma: traditional public-key schemes like ECDSA provide strong security but impose 2 ms verification delays unsuitable for collision avoidance, while symmetric approaches like TESLA achieve microsecond-level efficiency at the cost of 20-100 ms key disclosure latency. Neither meets 5G New Radio (NR)-V2X's stringent requirements for both immediate authentication and computational efficiency. This paper presents SALT-V, a novel hybrid authentication framework that reconciles this fundamental trade-off through intelligent protocol stratification. SALT-V employs ECDSA signatures for 10% of traffic (BOOT frames) to establish sender trust, then leverages this trust anchor to authenticate 90% of messages (DATA frames) using lightweight GMAC operations. The core innovation - an Ephemeral Session Tag (EST) whitelist mechanism - enables 95% of messages to achieve immediate verification without waiting for key disclosure, while Bloom filter integration provides O(1) revocation checking in 1 us. Comprehensive evaluation demonstrates that SALT-V achieves 0.035 ms average computation time (57x faster than pure ECDSA), 1 ms end-to-end latency, 41-byte overhead, and linear scalability to 2000 vehicles, making it the first practical solution to satisfy all safety-critical requirements for real-time V2X deployment.

Nowadays, regulatory compliance has become a cornerstone of corporate governance, ensuring adherence to systematic legal frameworks. At its core, financial regulations often comprise highly intricate provisions, layered logical structures, and numerous exceptions, which inevitably result in labor-intensive or comprehension challenges. To mitigate this, recent Regulatory Technology (RegTech) and Large Language Models (LLMs) have gained significant attention in automating the conversion of regulatory text into executable compliance logic. However, their performance remains suboptimal particularly when applied to Chinese-language financial regulations, due to three key limitations: (1) incomplete domain-specific knowledge representation, (2) insufficient hierarchical reasoning capabilities, and (3) failure to maintain temporal and logical coherence. One promising solution is to develop a domain specific and code-oriented dataset for model training. Existing datasets such as LexGLUE, LegalBench, and CODE-ACCORD are often English-focused, domain-mismatched, or lack fine-grained granularity for compliance code generation. To fill these gaps, we present Compliance-to-Code, the first large-scale Chinese dataset dedicated to financial regulatory compliance. Covering 1,159 annotated clauses from 361 regulations across ten categories, each clause is modularly structured with four logical elements-subject, condition, constraint, and contextual information-along with regulation relations. We provide deterministic Python code mappings, detailed code reasoning, and code explanations to facilitate automated auditing. To demonstrate utility, we present FinCheck: a pipeline for regulation structuring, code generation, and report generation. Compliance-to-Code establishes a new benchmark for LLM-based compliance automation. Experimental evaluation shows that GLM-4-9B-0414 achieves the best performance on key task in regulation structuring and DeepSeek-R1-0528 performs the best in compliance code generation tasks.

With the rapid expansion of the Internet of Medical Things (IoMT) and cloud computing, ensuring secure communication in e-health systems has become increasingly critical. However, many existing authentication solutions suffer from excessive overhead and security vulnerabilities. To address these challenges, we present a lightweight, high-speed authentication protocol that relies on secure hash functions and XOR operations, facilitating efficient mutual authentication among users, trusted servers, and medical servers while establishing session keys for data exchange. We then rigorously assess our protocol's security against a comprehensive threat model, employing both informal methods and formal analyses, including Real-Or-Random (ROR) model, BAN logic, and automated verification via ProVerif. The results demonstrate that our protocol remains resilient against known attacks and satisfies e-health security standards. Furthermore, a detailed performance comparison reveals that our approach significantly reduces some costs compared to existing schemes, while reinforcing security and privacy protections.

Existing joint user association and trajectory control (JUATC) methods provide remarkably high data rates for mobile users (MUs) in unmanned aerial vehicle (UAV)-assisted multi-access edge computing systems. Nevertheless, current methods give more attention to the uplink and downlink of MU, which must be associated with the same UAV or base station (BS), ignoring the network’s heterogeneity and considerably reducing the MU’s communication efficiency. Furthermore, UAVs typically provide communication services to MUs under partial observation, leading to challenges in achieving optimal service performance due to information loss. Moreover, although existing solutions can readily reach optimal, restriction-fulfilling strategies, they frequently breach restrictions during intermediate iterations. To address these issues, we present a fully decentralized JUATC algorithm based on the Communication and Proportional-Integral-Derivative (PID) Lagrangian-based Multi-Agent Actor-Critic (CPID-MAAC). First, to improve communication efficiency, we consider that each MU can be associated with a different UAV or BS in the uplink and downlink. Second, we establish a messaging mechanism between UAVs based on autoencoding UAV’s observations to handle the information loss. Finally, to alleviate constraint-violating behavior, we incorporate the PID Lagrangian algorithm. The experiments show that CPID-MAAC improves data rate by 7.88%~16.03% and drastically reduces the number of constraint violations during UAV agent training.

With the rise of virtual communication and smart devices, speech has become the most natural medium of interaction. Yet it remains intrinsically difficult: speech is fleeting, unstructured, and disfluent, making key information prone to loss. Conventional Speech-to-Text (STT) systems attempt to acoustically reconstruct what was said. However, their frame-level alignment and rigid token-by-token decoding break down under noise, interruptions, or fragmentation. Humans, in contrast, readily grasp what was meant by exploiting syntax, discourse, pragmatics, and prosody. We argue for a paradigm shift from acoustic reconstruction to semantic transduction: inferring meaning directly from speech, abstracted from surface distortions. This shift raises two challenges: (C1) the lack of anchors between audio and meaning, and (C2) the need to maintain compositional semantics. To address these, we introduce CogTrans, a cognitively inspired speech-to-meaning framework. CogTrans tackles C1 through a Semantic Anchor Explorer, built on I-JEPA to capture higher-order regularities, prosodic rhythms, cross-frequency coarticulation, discourse continuity-providing resilient semantic scaffolds under noise and fragmentation. For C2, it designs a Lexical-Semantic Harmonizer that dynamically integrates these anchors with lexical embeddings; thereby preserving fine-grained compositional fidelity in roles, order, and entities. Extensive experiments show that CogTrans delivers consistent and substantial gains under challenging conditions. On GigaSpeech, it achieves a 6.58% relative Word Error Rate (WER) reduction, and on the multilingual VoxPopuli benchmark, the gain climbs to 12.97% at 10 dB noise-a regime where conventional models typically collapse. Beyond literal accuracy, CogTrans also boosts semantic fidelity, with a 3.40% increase in ROUGE-L and 3.45% in USE-Sim, ensuring transcripts remain faithful not only in words but also in meaning. Together, these results underscore that CogTrans is robust in noisy, unconstrained environments-precisely the conditions where reliability matters most.

Federated Learning (FL) enables decentralized model training while preserving data privacy. Despite its benefits, FL faces challenges with non-identically distributed (non-IID) data, especially in long-tailed scenarios with imbalanced class samples. Momentum-based FL methods, often used to accelerate FL convergence, struggle with these distributions, resulting in biased models and making FL hard to converge. To understand this challenge, we conduct extensive investigations into this phenomenon, accompanied by a layer-wise analysis of neural network behavior. Based on these insights, we propose FedWCM, a method that dynamically adjusts momentum using global and per-round data to correct directional biases introduced by long-tailed distributions. Extensive experiments show that FedWCM resolves non-convergence issues and outperforms existing methods, enhancing FL’s efficiency and effectiveness in handling client heterogeneity and data imbalance.

Global aging necessitates tele-monitoring systems to provide real-time tracking and timely assistance for older adults living independently. While pervasive wireless devices (e.g., CSI, IMU, UWB) enable cost-effective, non-intrusive monitoring, existing systems lack flexibility, limiting their adaptability to different environments. In this work, we posit that the motion dynamics of human movement are invariant across sensing modalities, inspiring the design of HARMONY—a privacy-preserving, sensor-agnostic system that supports multi-modal inputs and diverse tele-monitoring tasks. HARMONY incorporates Modality-agnostic Data Processing to uniformly encrypt multi-modal signals and Task-specific Activity Recognition for seamless tasks adaptation. A novel Encrypted-processing Engine then significantly accelerates computations on encrypted data by optimizing matrix and convolution operations. Evaluations across five different sensing modalities show that HARMONY consistently achieves high accuracy while delivering 3.5 × to 130 × speedups over state-of-the-art baselines. Our results demonstrate that HARMONY is a practical, scalable, and privacy-centric prototype for next-generation remote healthcare.

An emerging type of fraud involves malicious senders exploiting the blind shipment and cash-on-delivery (COD) mechanisms by dispatching large volumes of unsolicited, low-cost parcels. If unsuspecting receivers accept these parcels, they pay for both shipping and goods; otherwise, logistics providers bear the round-trip shipping costs. Existing detection techniques, which rely on extensive labeled cases, struggle with this emerging fraud because receivers' unawareness and low transaction values discourage complaints, resulting in few confirmed cases. Therefore, we propose leveraging receivers' complaints, though not initially collected for fraud detection, to uncover subtle indicators of fraud patterns, while addressing three challenges: (C1) noise-rich dialogues(C2) data privacy concerns, and (C3) ever-evolving fraud patterns. To address them, we design BLOFF, a Blind shipment detection Framework for LO gistics Fraud powered by large language models (LLMs). Specifically, BLOFF includes three components: i) Sensitivity Anonymization to protect sensitive user information; ii) Dialogue Profile Distillation to transform informal dialogues into structured representation, addressing C1, and distill knowledge from a teacher LLM (GPT-4o) to a lightweight student LLM (ChatGLM4-9B), addressing C2; ii) Multi-faceted Context Augmentation to enhance the interpretation of fraud signatures and adaptation of evolving patterns, addressing C3. We evaluate BLOFF on about 56,000 complaints records collected from JD Logistics between January and November 2024. Results show that BLOFF outperforms state-of-the-art methods, achieving a 10.19% improvement in precision. Furthermore, during its real-world deployment in December 2024, BLOFF identified over 90 fraudulent parcels with a 91.4% precision.

In federated learning (FL), models must \emph{converge quickly} under tight communication budgets while \emph{generalizing} across non-IID client distributions. These twin requirements have naturally led to two widely used techniques: client/server \emph{momentum} to accelerate progress, and \emph{sharpness-aware minimization} (SAM) to prefer flat solutions. However, simply combining momentum and SAM leaves two structural issues unresolved in non-IID FL. We identify and formalize two failure modes: \emph{local–global curvature misalignment} (local SAM directions need not reflect the global loss geometry) and \emph{momentum-echo oscillation} (late-stage instability caused by accumulated momentum). To our knowledge, these failure modes have not been jointly articulated and addressed in the FL literature. We propose \textbf{FedWMSAM} to address both failure modes. First, we construct a momentum-guided global perturbation from server-aggregated momentum to align clients' SAM directions with the global descent geometry, enabling a \emph{single-backprop} SAM approximation that preserves efficiency. Second, we couple momentum and SAM via a cosine-similarity adaptive rule, yielding an early-momentum, late-SAM two-phase training schedule. We provide a non-IID convergence bound that \emph{explicitly models the perturbation-induced variance} $\sigma_\rho^2=\sigma^2+(L\rho)^2$ and its dependence on $(S,K,R,N)$ on the theory side. We conduct extensive experiments on multiple datasets and model architectures, and the results validate the effectiveness, adaptability, and robustness of our method, demonstrating its superiority in addressing the optimization challenges of Federated Learning. Our code is available at \url{https://github.com/Li-Tian-Le/NeurlPS_FedWMSAM}.

Vehicular Ad-hoc Networks (VANETs) face significant security and privacy challenges in modern intelligent transportation systems. This paper analyzes vulnerabilities in Al-Shareeda et al.'s vehicle authentication protocol (doi: 10.1109/TDSC.2025.3553868) and proposes an enhanced ECC-based scheme using short-lived pseudonymous certificates. We identify two critical weaknesses in Al-Shareeda et al.'s protocol—a desynchronization attack causing potential denial-of-service and an identity linking attack compromising vehicle privacy. Our protocol establishes mutual authentication between vehicles and roadside units, ensuring message integrity, anonymity, and perfect forward secrecy. Unlike existing approaches, it eliminates the need for online third-party authenticators. Formal security proofs demonstrate that the scheme's security is reducible to the hardness of the ECDLP and CDH problems. Performance analysis shows our approach achieves an optimal security-efficiency balance with competitive communication overhead (4608 bits) and computation costs (5.02 ms) compared to state-of-the-art alternatives, while uniquely satisfying all twelve evaluated security properties.

The increasing integration of Internet of Things (IoT) devices in Wireless Local Area Networks (WLANs) necessitates robust and efficient authentication mechanisms. While existing IoT authentication protocols address certain security concerns, they often fail to provide comprehensive protection against threats such as perfect forward secrecy violations, insider attacks, and key compromise impersonation, or impose significant computational and communication overhead on resource-constrained IoT systems. This paper presents a novel Extensible Authentication Protocol (EAP) based scheme for IoT-WLAN environments that addresses these security challenges while maintaining cost-effectiveness. Our approach utilizes elliptic curve cryptography and incorporates advanced features including perfect forward secrecy, strong identity protection, and explicit key confirmation. We provide a thorough security analysis using informal heuristics, formal methods (Random Oracle Model and BAN Logic), and automated verification with ProVerif. Performance evaluations demonstrate that our protocol achieves lower communication, storage, and computational costs compared to state-of-the-art solutions, with an average 79.6% reduction in computation time. A detailed comparison with existing schemes highlights the efficiency and enhanced security features of our proposed authentication mechanism for IoT-WLAN deployments.

Variable selection for genome-wide association studies (GWAS) has been a major research focus for decades. With the exponential growth of biological and biomedical data in the era of big data, scientists are confronted with the challenge of extracting meaningful information from vast datasets while managing the inherent heterogeneity in bioinformatics. To date, there are no highly effective tools that support high-dimensional datasets and achieve robust variable selection performance, all while accounting for the non-i.i.d. features and structured relatedness among explanatory and response variables.To address these challenges, we introduce the first high-performance computing framework for variable selection in GWAS. Our framework integrates various state-of-the-art methods, allowing researchers to easily combine different techniques and fully explore their potential. Additionally, our approach employs novel optimization strategies to solve the problem efficiently, even for high-dimensional data with sparse characteristics. By processing the data holistically, the framework delivers comprehensive analysis and accurate linkage mapping associations. Designed for ease of use, the framework is implemented in Python and offers seamless deployment, making it accessible to a wide range of researchers.

The integration of 5G/6G networks with intelligent healthcare systems has enabled early disease detection through patient data monitoring. However, the Internet of Medical Things (IoMT) and remote healthcare services introduce significant privacy and security risks. In this paper, we propose LiteCrypt, which addresses these challenges by introducing an optimized Homomorphic Convolutional Neural Networks (HCNN) structure for secure inference and a lightweight Threshold Signature Scheme (TSS) based dual-authorization mechanism. To enhance the practicality of Homomorphic Encryption (HE)-based secure inference in telemedicine applications, LiteCrypt presents an optimized HCNN framework that ensures efficient and adaptable operations across multiple datasets. A high-performance GPU-accelerated HE engine is developed to address the computational demands of HE operations, enabling real-time processing of encrypted patient data. Besides, LiteCrypt introduces a novel TSS-based dual-authorization protocol, requiring consent from both the patient and the hospital to access patient data, thereby mitigating unauthorized access risks. The system adapts to a flexible 2-out-of-3 authorization scheme for emergencies, ensuring timely data retrieval while maintaining security. To overcome the initial challenge of prolonged computation time due to compute-intensive operations, In LiteCrypt, we utilized the lightweight TSS protocol, based on Oblivious Transfer (OT), which is designed for resource-constrained IoMT devices, reducing computation time from 11.9 to 0.11 seconds. Empirical validation demonstrates LiteCrypt’s superior performance, achieving a 233-fold increase in processing speed, a $96 \%$ reduction in encrypted message size, and a 28-fold speed increase using GPUs.

Keystroke dynamics has proven to be highly effective, with its applications expanding significantly over the years in areas such as preventing transaction fraud, account takeovers, and identity theft. Key-positioning and feature-learning methods are commonly used to identify keystroke signals. However, the existing methods face challenges in detecting overlapping keystrokes and environmentally changed signals. We propose a solution called Chameleon to address these limitations. Unlike previous signal separation and deep learning methods that are ineffective in keystroke signals and computationally demanding, Chameleon employs a low-computation Ranking Model to separate overlapping keystroke signals. Moreover, our experiments demonstrate that Chameleon separated signals can be recognized with an average accuracy of 92.69%, surpassing the commonly used FastICA method, which only reaches 25% accuracy. To account for environmental changes, we utilize the Fréchet Inception Distance (FID) as a guiding metric for model migration. Additionally, we introduce the Inductive Vector, which enables our key-identifying model to adapt to altered environmental conditions such as environment, phone location, and user variety. The Inductive Vector adjusts the model parameters based on the shift in FID. In scenarios with various phone locations, the Inductive Vector significantly improves recognition accuracy from 61% to 98%, outperforming the best existing keystroke recognition algorithm. In other dynamic environmental conditions, our approach achieves an average accuracy rate of 81.7%, which is at least 1.6 times better than the current state-of-the-art keystroke recognition algorithm.

With the advancement of the Internet of Medical Things (IoMT) and cryptographic technologies, remote healthcare services have become more widespread, presenting new challenges for patient privacy and data security. Conventional security mechanisms, such as centralized authentication and key distribution systems, are susceptible to single points of failure and significant management burdens, potentially leading to compromised authentication centers and internal security threats. In response, this study presents a threshold signature algorithm, it uses Distributed Key Generation (DKG) that distributes private keys without the need for a trusted key distributor, requiring the cooperative signature of at least two nodes for authentication. This approach not only circumvents the risk of single points of failure but also enhances the system’s robustness and efficiency. The experimental results validate its prospective utility in safeguarding remote healthcare data.

Federated learning (FL) offers distributed machine learning on edge devices. However, the FL model raises privacy concerns. Various techniques, such as homomorphic encryption (HE), differential privacy, and multiparty cooperation, are used to address the privacy issues of the FL model. Among them, HE ensures greater security and privacy since end-to-end encryption maintains data privacy throughout the computation process. Compared with other privacy-preserving techniques, HE does not require the establishment of a trusted environment or protocol among multiple parties and does not involve any artificial noise that can impair system performance. Unfortunately, it suffers from efficiency overhead when applied to privacy-preserving FL (PPFL). Some existing surveys on PPFL discuss the generic construction and organization of PPFL from the perspective of practical HE deployment in PPFL. However, none of them covers the efficiency optimization of HE when applied to PPFL. This article conducts a comprehensive review of the efficiency optimization of HE when applied to PPFL. First, we review general optimization strategies and discuss their limitations when applied directly to HE-based PPFL. Second, an overview of algorithmic, hardware, and hybrid optimizations is provided, along with a discussion of their adaptation. Additionally, we provide a detailed taxonomy of optimizations. Finally, we suggest future HE-based PPFL research directions.

The rapid development of AI applications powered by deep learning in edge devices boosts the opportunity for real-time health monitoring. To address the potential privacy concern in the inference phase, homomorphic encryption (HE) is an alternative solution that encrypts inference data without exposing raw data and has several distinct advantages, (i.e., single-round communication, lightweight bandwidth consumption, and non-interactive computation). However, the computational overhead on the current HE-based privacy-preserving inference necessitates a substantial amount of time, which is not feasible for some real-time applications on edge devices. To address this issue, we propose CNN-guardian, a unified and compact neural network structure for real-time inference in HE-based inference on edge GPU. CNN-guardian designs a HE-friendly neural network and GPU engine that optimizes HE operations to accelerate the inference in the HE domain.

The Elliptic Curve Digital Signature Algorithm (ECDSA) is an essential building block of various cryptographic protocols. In particular, most blockchain systems adopt it to ensure transaction integrity. However, due to its high computational intensity, ECDSA is often the performance bottleneck in blockchain transaction processing. Recent work has accelerated ECDSA algorithms on the CPU; in contrast, success has been limited on the GPU, which has great potential for parallelization but is challenging for implementing elliptic curve functions. In this paper, we propose RapidEC, a GPU-based ECDSA implementation for SM2, a popular elliptic curve. Specifically, we design architecture-aware parallel primitives for elliptic curve point operations, and parallelize the processing of a single SM2 request as well as batches of requests. Consequently, our GPU-based RapidEC outperformed the state-of-the-art CPU-based algorithm by orders of magnitude. Additionally, our GPU-based modular arithmetic functions as well as point operation primitives can be applied to other computation tasks.