arXiv subjects

Meng Shen

Publications and source records attributed to Meng Shen.

At least 19 recordsLinked to original sources

arXiv2026

Heterogeneous Cross-Chain Transaction Tracing for Solana Bridges via Candidate-Set Selective Decision

Solana is a rapidly growing high-throughput blockchain platform that has attracted substantial liquidity and user activity. However, this expansion has also drawn the attention of illicit actors, who frequently leverage cross-chain bridges to route illicit funds onto Solana to obfuscate transaction lineage. Unlike EVM-compatible platforms, Solana features distinct execution dynamics and lacks standard event logs, creating severe semantic gaps that prevent existing tracing methods from reliably correlating cross-ledger transactions. In this paper, we formalize four types of Solana-bound cross-chain transaction modes and propose a candidate-set selective decision-based tracing method called SolTracer. SolTracer maps disparate execution semantics into a unified event space and employs candidate-set selective decision-making to reliably associate target transactions while abstaining when valid targets are absent. Extensive experiments demonstrate that SolTracer outperforms state-of-the-art (SOTA) methods across three representative scenarios: closed-world association, open-world association, and cross-source-chain generalization. In particular, under the challenging open-world setting with a 50% TA ratio, SolTracer improves the F1 score by 20.16% over the strongest SOTA baseline. Utilizing SolTracer, we conduct an empirical analysis on real-world cross-chain transfers to investigate ecosystem dynamics. Our analysis explores the stark count-value divergence across bridge mechanisms, the prevalence of cross-asset shifts, and the decoupling between on-chain settlement and explorer visibility.

cs.CR↗

arXiv2026

SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing

In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on predefined risk taxonomies. In this work, we study this setting under the paradigm of in-context policy guardrailing, where guardrails predict safety violations based on policy specifications provided in context. To systematically evaluate this capability, we introduce SafePyramid, a safety benchmark comprising 1,000 multi-turn conversations across 10 domains and 3,000 corresponding application-specific policies, which together contain 61,699 distinct natural-language rules. SafePyramid organizes the evaluation into three difficulty levels: L0 evaluates individual-rule understanding, L1 evaluates reasoning over rule dependencies, and L2 evaluates adaptation of full novel policy frameworks defined in context. To ensure benchmark quality, we employ a rigorous multi-stage pipeline to construct and validate the benchmark. Using SafePyramid, we evaluate 10 frontier LLMs and 5 policy-configurable guardrails and find that in-context policy guardrailing remains highly challenging: even the best-performing model, GPT-5.5, exactly identifies the full set of violated rules in only 54.0%, 35.3%, and 12.9% cases on L0, L1, and L2, respectively. These results highlight the limitations of current guardrails and call for stronger in-context policy guardrails that can reliably execute policies, resolve rule dependencies, and adapt to novel policy frameworks.

cs.AI↗

arXiv2026

Towards World Model-Empowered Integrated Sensing, Communication, and Decision for Complex Unmanned Systems

Complex unmanned systems comprising satellites, unmanned aerial vehicles (UAVs), unmanned ground vehicles (UGVs), and quadruped robots are increasingly deployed to perform large-scale sensing and autonomous operations. We propose a world model-empowered sensing, communication, decision (SCD) integration framework for complex unmanned communication networks. The proposed architecture establishes a closed-loop system where a unified world model jointly optimizes time-sensitive sensing, wireless communication, and intelligent decision-making. To regulate sensing freshness and reduce redundant data generation, we propose a time-sensitive age of information (AoI)-driven sensing mechanism that dynamically schedules sensing updates based on task urgency and predictive uncertainty. Furthermore, a predictive world model is developed to jointly represent environmental dynamics, wireless channel evolution, and agent mobility within a hybrid deterministic-stochastic latent space. This enables proactive communication scheduling and decision evaluation via latent rollout. To support large-scale heterogeneous coordination, a multi-granularity knowledge graph is further designed to organize cross-population relationships among satellites, UAVs, UGVs, and ground agents. Numerical results demonstrate that the proposed SCD framework outperforms conventional systems, highlighting the significant potential of world models for supporting unmanned systems.

cs.IT↗

arXiv2026

Tunable supramolecular polymerization from protein charge heterogeneity and architecture

Multidomain proteins with flexible unstructured sequence regions are abundant in cellular signaling. This protein architecture enables self-assembly into supramolecular structures, but how structured interaction domains and overall protein architecture jointly regulate the assembly size, structure and kinetics remains unclear. Here we use the budding yeast protein Bem1 as a model multidomain system to show that supramolecular polymerization can be tuned by charge heterogeneity and protein architecture. We experimentally demonstrate that Bem1's isolated PB1 domain forms extended filaments, whereas full-length Bem1 forms substantially shorter assemblies, indicating that the PB1 domain drives assembly while the remaining protein architecture tunes filament length. To understand these observations, we develop minimal coarse-grained models approximating the PB1 as a polar 5-bead domain and the full-length Bem1 as a 6-bead model with an additional bead representing the remainder of Bem1. The weight distribution of supramolecular filaments assembled by the 5-bead model quantitatively follows reversible Flory-like polymerization theory, which is tunable within a narrow charge polarity regime. In contrast, the 6-bead model shifts chain-length distributions towards shorter polymers despite retaining the same driving domain. We show that this deviation arises from steric and geometric constraints imposed by the appended unstructured regions, where the rotational flexibility between the charge-polar structured domain and the unstructured region emerges as key physical parameter governing self-limited self-assembly. Together, our results establish charge polarity, protein architecture, and conformational flexibility as programmable control knobs for supramolecular polymerization and suggest a general framework for understanding how multidomain proteins assemble into tunable biomolecular structures.

cond-mat.soft↗

arXiv2026

Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens

Object hallucination is a significant challenge that hinders the application of large vision-language models (LVLMs) in practice. We hypothesize that one possible origin of hallucination is the model's tendency to prioritize text generation over meaningful interaction with images. To explore this, we examine the generation process and categorize text tokens into three groups: image-positive, invariant, and negative, based on their visual dependence on input image tokens. Our analysis reveals that most generated tokens are minimally influenced by the image information. This suggests that during the model's training stage, more emphasis is placed on learning how to follow textual instructions, rather than extracting information from images. Based on this finding, we propose adjusting the training weights of different tokens depending on their visual dependence to control hallucination. Additionally, we remove a portion of the training data that potentially contains more hallucinations as a data filtering strategy. Both methods achieve a reduction in hallucination without compromising response length or introducing additional computational costs during inference. We validate our methods across three LVLM variants, demonstrating the effectiveness and general applicability.

cs.CV↗

arXiv2026

Roadmap for Condensates in Cell Biology

Biomolecular condensates govern essential cellular processes yet elude description by traditional equilibrium models. This roadmap, distilled from structured discussions at a workshop and reflecting the consensus of its participants, clarifies key concepts for researchers, funding bodies, and journals. After unifying terminology that often separates disciplines, we outline the core physics of condensate formation, review their biological roles, and identify outstanding challenges in nonequilibrium theory, multiscale simulation, and quantitative in-cell measurements. We close with a forward-looking outlook to guide coordinated efforts toward predictive, experimentally anchored understanding and control of biomolecular condensates.

physics.bio-ph↗

arXiv2026

Traffic-MoE: A Sparse Foundation Model for Network Traffic Security Analysis

As adversaries increasingly weaponize encryption and protocol obfuscation to evade traffic detection, traditional methods are rendered obsolete, necessitating deep learning to unmask sophisticated threats. However, the prohibitive computational costs of existing large models create a critical defense gap, hindering their deployment in real-time and throughput-sensitive environments. To close this vulnerability, we introduce Traffic-MoE, a sparse foundation model tailored for traffic security analysis. By dynamically routing traffic tokens to a small subset of specialized experts, Traffic-MoE effectively decouples model capacity from computational overhead. Extensive evaluations across four security-oriented tasks demonstrate that Traffic-MoE achieves state-of-the-art or highly competitive performance compared to leading competitors. Crucially, it delivers a 70.42% increase in throughput, reduces inference latency by 41.39% while significantly optimizing GPU memory consumption. Beyond efficiency, Traffic-MoE exhibits superior robustness against adversarial traffic shaping and maintains strong detection capabilities in few-shot scenarios, establishing a scalable and resilient paradigm for modern network traffic security analysis.

cs.CR↗

arXiv2025

Hierarchical Schedule Optimization for Fast and Robust Diffusion Model Sampling

Diffusion probabilistic models have set a new standard for generative fidelity but are hindered by a slow iterative sampling process. A powerful training-free strategy to accelerate this process is Schedule Optimization, which aims to find an optimal distribution of timesteps for a fixed and small Number of Function Evaluations (NFE) to maximize sample quality. To this end, a successful schedule optimization method must adhere to four core principles: effectiveness, adaptivity, practical robustness, and computational efficiency. However, existing paradigms struggle to satisfy these principles simultaneously, motivating the need for a more advanced solution. To overcome these limitations, we propose the Hierarchical-Schedule-Optimizer (HSO), a novel and efficient bi-level optimization framework. HSO reframes the search for a globally optimal schedule into a more tractable problem by iteratively alternating between two synergistic levels: an upper-level global search for an optimal initialization strategy and a lower-level local optimization for schedule refinement. This process is guided by two key innovations: the Midpoint Error Proxy (MEP), a solver-agnostic and numerically stable objective for effective local optimization, and the Spacing-Penalized Fitness (SPF) function, which ensures practical robustness by penalizing pathologically close timesteps. Extensive experiments show that HSO sets a new state-of-the-art for training-free sampling in the extremely low-NFE regime. For instance, with an NFE of just 5, HSO achieves a remarkable FID of 11.94 on LAION-Aesthetics with Stable Diffusion v2.1. Crucially, this level of performance is attained not through costly retraining, but with a one-time optimization cost of less than 8 seconds, presenting a highly practical and efficient paradigm for diffusion model acceleration.

cs.LG↗

arXiv2025

Label Inference Attacks against Federated Unlearning

Federated Unlearning (FU) has emerged as a promising solution to respond to the right to be forgotten of clients, by allowing clients to erase their data from global models without compromising model performance. Unfortunately, researchers find that the parameter variations of models induced by FU expose clients' data information, enabling attackers to infer the label of unlearning data, while label inference attacks against FU remain unexplored. In this paper, we introduce and analyze a new privacy threat against FU and propose a novel label inference attack, ULIA, which can infer unlearning data labels across three FU levels. To address the unique challenges of inferring labels via the models variations, we design a gradient-label mapping mechanism in ULIA that establishes a relationship between gradient variations and unlearning labels, enabling inferring labels on accumulated model variations. We evaluate ULIA on both IID and non-IID settings. Experimental results show that in the IID setting, ULIA achieves a 100% Attack Success Rate (ASR) under both class-level and client-level unlearning. Even when only 1% of a user's local data is forgotten, ULIA still attains an ASR ranging from 93% to 62.3%.

cs.CR↗

arXiv2025

Versatile yet Efficient Network Traffic Analysis: Offloading Network Foundation Model to SmartNIC

Pervasive encryption makes large-scale labeling infeasible for traffic analysis, while security operations demand edge analysis to avert service degradation and further vulnerabilities. These pressures have produced two disjoint research lines: 1) versatile analysis, via network foundation models for low label dependency, and 2) efficient analysis, via hardware offloading for low analysis latency. However, versatility and efficiency have appeared fundamentally incompatible to co-achieve, with prior work consistently sacrificing one for the other, yet we show that this incompatibility is a consequence of polarized design choices across the three components of traffic analysis systems, i.e., traffic processing, model architecture, and analysis execution. In response, we present Nepco, a versatile yet efficient network traffic analysis system that offloads network foundation models to SmartNIC. Our key observation is that discriminative traffic information is concentrated in localized byte regions, motivating versatile yet efficient localized byte-sequence modeling rather than inefficient global modeling. To exploit this without incurring the latency bottlenecks of complex encoding steps, we employ a hardware-friendly processing pipeline that directly embeds raw byte sequences. Crucially, to maintain versatility across diverse tasks, we propose a pattern-aware convolutional architecture equipped with dedicated scoring and gating mechanisms. By exploiting translation invariance, this design dynamically locates and extracts salient semantic signatures. We prototype Nepco on the Nvidia BlueField-3 SmartNIC with multiengine collaborative analysis execution. The experimental results demonstrate that Nepco achieves macro F1 competitive with the best performances achieved by 8 state-of-the-art network foundation models, while reducing end-to-end latency by 328x to the millisecond scale.

cs.NI↗

arXiv2025

S-Leak: Leakage-Abuse Attack Against Efficient Conjunctive SSE via s-term Leakage

Conjunctive Searchable Symmetric Encryption (CSSE) enables secure conjunctive searches over encrypted data. While leakage-abuse attacks (LAAs) against single-keyword SSE have been extensively studied, their extension to conjunctive queries faces a critical challenge: the combinatorial explosion of candidate keyword combinations, leading to enormous time and space overhead for attacks. In this paper, we reveal a fundamental vulnerability in state-of-the-art CSSE schemes: s-term leakage, where the keyword with the minimal document frequency in a query leaks distinct patterns. We propose S-Leak, the first passive attack framework that progressively recovers conjunctive queries by exploiting s-term leakage and global leakage. Our key innovation lies in a three-stage approach: identifying the s-term of queries, pruning low-probability keyword conjunctions, and reconstructing full queries. We propose novel metrics to better assess attacks in conjunctive query scenarios. Empirical evaluations on real-world datasets demonstrate that our attack is effective in diverse CSSE configurations. When considering 161,700 conjunctive keyword queries, our attack achieves a 95.15% accuracy in recovering at least one keyword, 82.57% for at least two, 58% for all three keywords, and maintains efficacy against defenses such as SEAL padding and CLRZ obfuscation. Our work exposes the underestimated risks of s-term leakage in practical SSE deployments and calls for a redesign of leakage models for multi-keyword search scenarios.

cs.CR↗

arXiv2025

Language of Network: A Generative Pre-trained Model for Encrypted Traffic Comprehension

The increasing demand for privacy protection and security considerations leads to a significant rise in the proportion of encrypted network traffic. Since traffic content becomes unrecognizable after encryption, accurate analysis is challenging, making it difficult to classify applications and detect attacks. Deep learning is currently the predominant approach for encrypted traffic classification through feature analysis. However, these methods face limitations due to their high dependence on labeled data and difficulties in detecting attack variants. First, their performance is highly sensitive to data quality, where the highcost manual labeling process and dataset imbalance significantly degrade results. Second, the rapid evolution of attack patterns makes it challenging for models to identify new types of attacks. To tackle these challenges, we present GBC, a generative model based on pre-training for encrypted traffic comprehension. Since traditional tokenization methods are primarily designed for natural language, we propose a protocol-aware tokenization approach for encrypted traffic that improves model comprehension of fields specific to network traffic. In addition, GBC employs pretraining to learn general representations from extensive unlabeled traffic data. Through prompt learning, it effectively adapts to various downstream tasks, enabling both high-quality traffic generation and effective detection. Evaluations across multiple datasets demonstrate that GBC achieves superior results in both traffic classification and generation tasks, resulting in a 5% improvement in F1 score compared to state-of-the-art methods for classification tasks.

cs.CR↗

arXiv2025

Correlating Account on Ethereum Mixing Service via Domain-Invariant feature learning

The untraceability of transactions facilitated by Ethereum mixing services like Tornado Cash poses significant challenges to blockchain security and financial regulation. Existing methods for correlating mixing accounts suffer from limited labeled data and vulnerability to noisy annotations, which restrict their practical applicability. In this paper, we propose StealthLink, a novel framework that addresses these limitations through cross-task domain-invariant feature learning. Our key innovation lies in transferring knowledge from the well-studied domain of blockchain anomaly detection to the data-scarce task of mixing transaction tracing. Specifically, we design a MixFusion module that constructs and encodes mixing subgraphs to capture local transactional patterns, while introducing a knowledge transfer mechanism that aligns discriminative features across domains through adversarial discrepancy minimization. This dual approach enables robust feature learning under label scarcity and distribution shifts. Extensive experiments on real-world mixing transaction datasets demonstrate that StealthLink achieves state-of-the-art performance, with 96.98\% F1-score in 10-shot learning scenarios. Notably, our framework shows superior generalization capability in imbalanced data conditions than conventional supervised methods. This work establishes the first systematic approach for cross-domain knowledge transfer in blockchain forensics, providing a practical solution for combating privacy-enhanced financial crimes in decentralized ecosystems.

cs.CR↗

arXiv2024

Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning

Training multimodal models requires a large amount of labeled data. Active learning (AL) aim to reduce labeling costs. Most AL methods employ warm-start approaches, which rely on sufficient labeled data to train a well-calibrated model that can assess the uncertainty and diversity of unlabeled data. However, when assembling a dataset, labeled data are often scarce initially, leading to a cold-start problem. Additionally, most AL methods seldom address multimodal data, highlighting a research gap in this field. Our research addresses these issues by developing a two-stage method for Multi-Modal Cold-Start Active Learning (MMCSAL). Firstly, we observe the modality gap, a significant distance between the centroids of representations from different modalities, when only using cross-modal pairing information as self-supervision signals. This modality gap affects data selection process, as we calculate both uni-modal and cross-modal distances. To address this, we introduce uni-modal prototypes to bridge the modality gap. Secondly, conventional AL methods often falter in multimodal scenarios where alignment between modalities is overlooked. Therefore, we propose enhancing cross-modal alignment through regularization, thereby improving the quality of selected multimodal data pairs in AL. Finally, our experiments demonstrate MMCSAL's efficacy in selecting multimodal data pairs across three multimodal datasets.

cs.MM↗

arXiv2024

EVeCA: Efficient and Verifiable On-Chain Data Query Framework Using Challenge-Based Authentication

As blockchain applications become increasingly widespread, there is a rising demand for on-chain data queries. However, existing schemes for on-chain data queries face a challenge between verifiability and efficiency. Queries on blockchain databases can compromise the authenticity of the query results, while schemes that utilize on-chain Authenticated Data Structure (ADS) have lower efficiency. To overcome this limitation, we propose an efficient and verifiable on-chain data query framework EVeCA. In our approach, we free the full nodes from the task of ADS maintenance by delegating it to a limited number of nodes, and full nodes verify the correctness of ADS by using challenge-based authentication scheme instead of reconstructing them, which prevents the service providers from maintaining incorrect ADS with overwhelming probability. By carefully designing the ADS verification scheme, EVeCA achieves higher efficiency while remaining resilient against adaptive attacks. Our framework effectively eliminates the need for on-chain ADS maintenance, and allows full nodes to participate in ADS maintenance in a cost-effective way. We demonstrate the effectiveness of the proposed scheme through security analysis and experimental evaluation. Compared to existing schemes, our approach improves ADS maintenance efficiency by about 20*.

cs.CR↗

arXiv2024

Across-Platform Detection of Malicious Cryptocurrency Transactions via Account Interaction Learning

With the rapid evolution of Web3.0, cryptocurrency has become a cornerstone of decentralized finance. While these digital assets enable efficient and borderless financial transactions, their pseudonymous nature has also attracted malicious activities such as money laundering, fraud, and other financial crimes. Effective detection of malicious transactions is crucial to maintaining the security and integrity of the Web 3.0 ecosystem. Existing malicious transaction detection methods rely on large amounts of labeled data and suffer from low generalization. Label-efficient and generalizable malicious transaction detection remains a challenging task. In this paper, we propose ShadowEyes, a novel malicious transaction detection method. Specifically, we first propose a generalized graph structure named TxGraph as a representation of malicious transaction, which captures the interaction features of each malicious account and its neighbors. Then we carefully design a data augmentation method tailored to simulate the evolution of malicious transactions to generate positive pairs. To alleviate account label scarcity, we further design a graph contrastive mechanism, which enables ShadowEyes to learn discriminative features effectively from unlabeled data, thereby enhancing its detection capabilities in real-world scenarios. We conduct extensive experiments using public datasets to evaluate the performance of ShadowEyes. The results demonstrate that it outperforms state-of-the-art (SOTA) methods in four typical scenarios. Specifically, in the zero-shot learning scenario, it can achieve an F1 score of 76.98% for identifying gambling transactions, surpassing the SOTA method by12.05%. In the scenario of across-platform malicious transaction detection, ShadowEyes maintains an F1 score of around 90%, which is 10% higher than the SOTA method.

cs.CR↗

arXiv2024

Blockchain Takeovers in Web 3.0: An Empirical Study on the TRON-Steem Incident

A fundamental goal of Web 3.0 is to establish a decentralized network and application ecosystem, thereby enabling users to retain control over their data while promoting value exchange. However, the recent Tron-Steem takeover incident poses a significant threat to this vision. In this paper, we present a thorough empirical analysis of the Tron-Steem takeover incident. By conducting a fine-grained reconstruction of the stake and election snapshots within the Steem blockchain, one of the most prominent social-oriented blockchains, we quantify the marked shifts in decentralization pre and post the takeover incident, highlighting the severe threat that blockchain network takeovers pose to the decentralization principle of Web 3.0. Moreover, by employing heuristic methods to identify anomalous voters and conducting clustering analyses on voter behaviors, we unveil the underlying mechanics of takeover strategies employed in the Tron-Steem incident and suggest potential mitigation strategies, which contribute to the enhanced resistance of Web 3.0 networks against similar threats in the future. We believe the insights gleaned from this research help illuminate the challenges imposed by blockchain network takeovers in the Web 3.0 era, suggest ways to foster the development of decentralized technologies and governance, as well as to enhance the protection of Web 3.0 user rights.

cs.SI↗

arXiv2024

The Illusion of Anonymity: Uncovering the Impact of User Actions on Privacy in Web3 Social Ecosystems

The rise of Web3 social ecosystems signifies the dawn of a new chapter in digital interaction, offering significant prospects for user engagement and financial advancement. Nonetheless, this progress is shadowed by potential privacy concessions, especially as these platforms frequently merge with existing Web2.0 social media accounts, amplifying data privacy risks for users. In this study, we investigate the nuanced dynamics between user engagement on Web3 social platforms and the consequent privacy concerns. We scrutinize the widespread phenomenon of fabricated activities, which encompasses the establishment of bogus accounts aimed at mimicking popularity and the deliberate distortion of social interactions by some individuals to gain financial rewards. Such deceptive maneuvers not only distort the true measure of the active user base but also amplify privacy threats for all members of the user community. We also find that, notwithstanding their attempts to limit social exposure, users remain entangled in privacy vulnerabilities. The actions of those highly engaged users, albeit often a minority group, can inadvertently breach the privacy of the larger collective. By casting light on the delicate interplay between user engagement, financial motives, and privacy issues, we offer a comprehensive examination of the intrinsic challenges and hazards present in the Web3 social milieu. We highlight the urgent need for more stringent privacy measures and ethical protocols to navigate the complex web of social exchanges and financial ambitions in the rapidly evolving Web3.

cs.CR↗