Papers

The current state, emerging trends, and practical challenges of optical fiber-based power network SCADA quantum communication must be addressed to fully utilize the technological platform's potential in real-world power system SCADA communications involving massive volumes of real-time data, as well as in managing, encoding, and applications such as quantum cryptography. Quantum key distribution (QKD) is an essential part of the cybersecurity paradigm for quantum communication. Even though quantum computing with individual circuits yields probabilistic outcomes for the problem at hand, real-world datasets are complex and challenging to handle, even with telemetry. When using the cybersecurity triad of availability, confidentiality, and integrity (CIA) in reverse order (AIC), availability is given priority in electric power networks. This research assesses the use of the BB84, E91, B92, and SARG04 cryptographic protocols by applying them to large, multivariate power-system SCADA datasets and comparing the outcomes. By leveraging the variety of QKD protocols available with quantum electronics hardware, this simulation work provides a promising avenue for developing implementable frameworks and deploying SCADA/PMU networks in actual power systems.

Dataset distillation compresses a large real dataset into a small synthetic one, enabling models trained on the synthetic data to achieve performance comparable to those trained on the real data. Although synthetic datasets are assumed to be privacy-preserving, we show that existing distillation methods can cause severe privacy leakage because synthetic datasets implicitly encode the weight trajectories of the distilled model, they become over-informative and exploitable by adversaries. To expose this risk, we introduce the Information Revelation Attack (IRA) against state-of-the-art distillation techniques. Experiments show that IRA accurately predicts both the distillation algorithm and model architecture, and can successfully infer membership and recover sensitive samples from the real dataset.

Self-supervised diffusion models learn high-quality visual representations via latent space denoising. However, their representation layer poses a distinct threat: unlike traditional attacks targeting generative outputs, its unconstrained latent semantic space allows for stealthy backdoors, permitting malicious control upon triggering. In this paper, we propose BadRSSD, the first backdoor attack targeting the representation layer of self-supervised diffusion models. Specifically, it hijacks the semantic representations of poisoned samples with triggers in Principal Component Analysis (PCA) space toward those of a target image, then controls the denoising trajectory during diffusion by applying coordinated constraints across latent, pixel, and feature distribution spaces to steer the model toward generating the specified target. Additionally, we integrate representation dispersion regularization into the constraint framework to maintain feature space uniformity, significantly enhancing attack stealth. This approach preserves normal model functionality (high utility) while achieving precise target generation upon trigger activation (high specificity). Experiments on multiple benchmark datasets demonstrate that BadRSSD substantially outperforms existing attacks in both FID and MSE metrics, reliably establishing backdoors across different architectures and configurations, and effectively resisting state-of-the-art backdoor defenses.

Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating software velocity and the limited adaptability of existing security tooling. Pattern-driven scanners fail to reason about novel contexts, while emerging LLM-based penetration testers rely on unconstrained exploration, yielding high cost, unstable behavior, and poor reproducibility. We introduce AWE, a memory-augmented multi-agent framework for autonomous web penetration testing that embeds structured, vulnerability-specific analysis pipelines within a lightweight LLM orchestration layer. Unlike general-purpose agents, AWE couples context aware payload mutations and generations with persistent memory and browser-backed verification to produce deterministic, exploitation-driven results. Evaluated on the 104-challenge XBOW benchmark, AWE achieves substantial gains on injection-class vulnerabilities - 87% XSS success (+30.5% over MAPTA) and 66.7% blind SQL injection success (+33.3%) - while being much faster, cheaper, and more token-efficient than MAPTA, despite using a midtier model (Claude Sonnet 4) versus MAPTA's GPT-5. MAPTA retains higher overall coverage due to broader exploratory capabilities, underscoring the complementary strengths of specialized and general-purpose architectures. Our results demonstrate that architecture matters as much as model reasoning capabilities: integrating LLMs into principled, vulnerability-aware pipelines yields substantial gains in accuracy, efficiency, and determinism for injection-class exploits. The source code for AWE is available at: https://github.com/stuxlabs/AWE

As quantum computing platforms increasingly adopt cloud-based execution, users submit quantum circuits to remote compilers and backends, trusting that what they submit is exactly what will be run. This shift introduces new trust assumptions in the submission pipeline, which remain largely unexamined. In this paper, we present QSpy, the first proof-of-concept Quantum Remote Access Trojan capable of intercepting quantum circuits in transit. Once deployed on a user's machine, QSpy silently installs a rogue certificate authority and proxies outgoing API traffic, enabling a man-in-the-middle (MITM) attack on submitted quantum circuits. We show that the intercepted quantum circuits may be forwarded to a remote server, which is capable of categorizing, storing, and analyzing them, without disrupting execution or triggering authentication failures. Our prototype targets IBM Qiskit APIs on a Windows system, but the attack model generalizes to other delegated quantum computing workflows. This work highlights the urgent need for submission-layer protections and demonstrates how even classical attack primitives can pose critical threats to quantum workloads.

Modern generative agents such as OpenClaw - an open-source, self-hosted personal assistant with a community skill ecosystem, are gaining attention and are used pervasively. However, the openness and rapid growth of these ecosystems often outpace systematic security evaluation. In this paper, we design, implement, and evaluate Clawdrain, a Trojanized skill that induces a multi-turn "Segmented Verification Protocol" via injected SKILL.md instructions and a companion script that returns PROGRESS/REPAIR/TERMINAL signals. We deploy Clawdrain in a production-like OpenClaw instance with real API billing and a production model (Gemini 2.5 Pro), and we measure 6-7x token amplification over a benign baseline, with a costly, failure configuration reaching approximately 9x. We observe a deployment-only phenomenon: the agent autonomously composes general-purpose tools (e.g., shell/Python) to route around brittle protocol steps, reducing amplification and altering attack dynamics. Finally, we identify production vectors enabled by OpenClaw's architecture, including SKILL.md prompt bloat, persistent tool-output pollution, cron/heartbeat frequency amplification, and behavioral instruction injection. Overall, we demonstrate that token-drain attacks remain feasible in real deployments, but their magnitude and observability are shaped by tool composition, recovery behavior, and interface design.

Smart contracts underpin high-value ecosystems such as decentralized finance (DeFi), yet recurring vulnerabilities continue to cause losses worth billions of dollars. Although numerous security analyzers that detect such flaws exist, real-world attacks remain frequent, raising the question of whether these tools are truly effective or simply under-used due to low developer trust. Prior benchmarks have evaluated analyzers on synthetic or vulnerable-only contract datasets, limiting their ability to measure false positives, false negatives, and usability factors that drive adoption. To close this gap, we present a mixed-methods study that combines large-scale benchmarking with practitioner insights. We evaluate six widely used analyzers (i.e., Confuzzius, Dlva, Mythril, Osiris, Oyente, and Slither) on 653 real-world smart contracts that cover three high-impact vulnerability classes from the OWASP Smart Contract Top Ten (i.e., reentrancy, suicidal contract termination, and integer arithmetic errors). Our results show substantial variation in accuracy (F1 = 31.2 to 94.6%), high false-positive rates (up to 32.6%), and runtimes exceeding 700 seconds per contract. We then survey 150 professional developers and auditors to understand how they use and perceive these tools. Our findings reveal that excessive false positives, vague explanations, and long analysis times are the main barriers to trust and adoption in practice. By linking measurable performance gaps to developer perceptions, we provide concrete recommendations for improving the precision, explainability, and usability of smart-contract security analyzers.

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply uniform detection strategies, which may not account for heterogeneous attack characteristics. This paper proposes an attack-aware multi-stage defense framework that learns attack-specific detection strategies through a weighted combination of ensemble disagreement, predictive uncertainty, and distributional anomaly signals. Empirical analysis across seven adversarial attack types reveals distinct detection signatures, enabling a two-stage adaptive detection mechanism. Experimental evaluation on a benchmark intrusion detection dataset indicates that the proposed system attains 94.2% area under the receiver operating characteristic curve and improves classification accuracy by 4.5 percentage points and F1-score by 9.0 points over adversarially trained ensembles. Under adaptive white-box attacks with full architectural knowledge, the system appears to maintain 94.4% accuracy with a 4.2% attack success rate, though this evaluation is limited to two adaptive variants and does not constitute a formal robustness guarantee. Cross-dataset validation further suggests that defense effectiveness depends on baseline classifier competence and may vary with feature dimensionality. These results suggest that attack-specific optimization combined with multi-signal integration can provide a practical approach to improving adversarial robustness in machine learning-based intrusion detection systems.

Accurate cardiovascular risk prediction is crucial for preventive healthcare; however, the development of robust Artificial Intelligence (AI) models is hindered by the fragmentation of clinical data across institutions due to stringent privacy regulations. This paper presents a comprehensive architectural case study validating the engineering robustness of FedCVR, a privacy-preserving Federated Learning framework applied to heterogeneous clinical networks. Rather than proposing a new theoretical optimizer, this work focuses on a systems engineering analysis to quantify the operational trade-offs of server-side adaptive optimization under utility-prioritized Differential Privacy (DP). By conducting a rigorous stress test in a high-fidelity synthetic environment that reflects the feature space and clinical context of real-world datasets (Framingham, Cleveland), we systematically evaluate the system's resilience to statistical noise. The validation results demonstrate that integrating server-side momentum as a temporal denoiser enables the architecture to achieve a stable F1 score of 0.78 and an Area Under the Curve (AUC) of 0.96 under the operational privacy budget (epsilon approximately 13.4), compared to a non-private baseline with an F1 score of 0.84. FedCVR statistically outperforms standard stateless baselines (FedAvg, FedProx) and other adaptive optimizers (FedAdagrad, FedYogi) under identical privacy constraints. Our findings confirm that server-side adaptivity is a structural prerequisite for recovering clinical utility under realistic privacy budgets, providing a validated engineering blueprint for secure multi-institutional collaboration.

Decentralized financial platforms rely heavily on Web of Trust reputation systems to mitigate counterparty risk in the absence of centralized identity verification. However, these pseudonymous networks are inherently vulnerable to adversarial behaviors, such as Sybil attacks and camouflaged fraud, where malicious actors cultivate artificial reputations before executing exit scams. Traditional anomaly detection in this domain faces two critical limitations. First, reliance on naive statistical heuristics (e.g., flagging the lowest 5% of rated users) fails to distinguish between victims of bad-mouthing attacks and actual fraudsters. Second, standard Graph Neural Networks (GNNs) operate on the assumption of homophily and cannot effectively process the semantic inversion inherent in signed (trust vs. distrust) and directed (status) edges. We propose TAS-GNN (Topology-Aware Signed Graph Neural Network), a novel framework designed for feature-sparse signed networks like Bitcoin-Alpha. TAS-GNN integrates recursive Web-of-Trust labeling and a dual-channel message-passing architecture that separately models trust and distrust signals, fused through a Status-Aware Attention mechanism. Experiments demonstrate that TAS-GNN achieves state-of-the-art performance, significantly outperforming existing signed GNN baselines.

The increasing incidence of IoT-based botnet attacks has driven interest in advanced learning models for detection. Recent efforts have focused on leveraging attention mechanisms to model long-range feature dependencies and Graph Neural Networks (GNNs) to capture relationships between data instances. Since GNNs require graph-structured input, tabular NetFlow data must be transformed accordingly. This study evaluates how the choice of the method for constructing the graph-structured dataset impacts the classification performance of a GNN model. Five methods–k-Nearest Neighbors, Mutual Nearest Neighbors, Shared Nearest Neighbor, Gabriel Graph, and epsilon-radius Graph–were evaluated in this research. To reduce the computational burden associated with high-dimensional data, a Variational Autoencoder (VAE) is employed to project the original features into a lower-dimensional latent space prior to graph generation. Subsequently, a Graph Attention Network (GAT) is trained on each graph to classify traffic in the N-BaIoT dataset into three categories: Normal, Mirai, and Gafgyt. The results indicate that using Gabriel graph achieves the highest detection performance with an accuracy of 97.56% while SNN recorded the lowest performance with an accuracy as low as 78.56%.

Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly focused on the detectable backdoor attacks. We propose a novel poisoning attack targeting the reasoning process of medical LLMs during SFT. Unlike backdoor attacks, our method injects poisoned rationales into few-shot training data, leading to stealthy degradation of model performance on targeted medical topics. Results showed that knowledge overwriting was ineffective, while rationale poisoning caused significant decline on the accuracy of the target subject, as long as no correct samples of the same subject appear in the dataset. A minimum number and ratio of poisoned samples was needed to carry out an effective and stealthy attack, which was more efficient and accurate than catastrophic forgetting. We demonstrate though this study the risk of SFT-stage poisoning, hoping to spur more studies of defense in the sensitive medical domain.

This article argues that security is not enough to fully capture what is at stake in government exceptional access to encrypted data. A conception of privacy as security has little to say about “lawful-surveillance protocols” – an active research agenda in cryptography that aims to enable government exceptional access without compromising systemic security. But the limitations are not contingent on the success of this agenda. The normative landscape today cannot be explained if security is all there is to privacy. And fundamental objections to Apple's abandoned client-side scanning system gesture beyond security. This article's contribution is modest: to show that there must be more to privacy than the security mold it has taken. A richer understanding is needed both to assess policy and to guide research on lawful-surveillance protocols.

Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we introduce a novel imperceptible universal backdoor attack that simultaneously controls all target classes with minimal poisoning while preserving stealth. Our key idea is to leverage graph convolutional networks (GCNs) to model inter-class relationships and generate class-specific perturbations that are both effective and visually invisible. The proposed framework optimizes a dual-objective loss that balances stealthiness (measured by perceptual similarity metrics such as PSNR) and attack success rate (ASR), enabling scalable, multi-target backdoor injection. Extensive experiments on ImageNet-1K with ResNet architectures demonstrate that our method achieves high ASR (up to 91.3%) under poisoning rates as low as 0.16%, while maintaining benign accuracy and evading state-of-the-art defenses. These results highlight the emerging risks of invisible universal backdoors and call for more robust detection and mitigation strategies.

Voting is the primary mechanism through which Decentralised Autonomous Organisations (DAOs) reach decisions. Although transparent, the voting process can be opaque: it can involve many interacting smart contracts. The nexus of the decision-making process can be relocated and the true voter demographic obfuscated. DAOs can also govern other DAOs, a process known as metagovernance. We present a method for identifying DAO-to-DAO metagovernance on the Ethereum blockchain. We focus on the links between DAOs and token contracts. We use a signature-matching algorithm to handle a variety of DAO frameworks and voting schemes. Once we establish token-to-DAO relationships, we gather and process voting data to produce a list of metagovernance relationships. We apply this algorithm to an initial set of sixteen DAOs and we extend the dataset as more DAOs are identified. We produce a metagovernance network with 61 DAOs and 72 metagovernance relationships. We examine three case studies that show metagovernance of various forms: strategic, decisive, and nexus, where a DAO becomes a governance hub for multiple other DAOs. We demonstrate that metagovernance obscures voting context and introduces entities driven by self-interest that can significantly influence governance. We highlight instances of metagovernance between DAOs operating on the Ethereum blockchain where current governance tools fail to reveal such dynamics. Better tools are needed to preserve the transparency-centric ethos of DAOs and mitigate risks associated with metagovernance.

Agent-native social platforms such as Moltbook are rapidly emerging, yet they inherit and amplify classical influence and abuse attacks, where coordinated agents strategically comment and upvote to manipulate visibility and propagate narratives across communities. However, rigorous measurement and learning-based monitoring remain constrained by the absence of longitudinal, graph-native datasets for agentic social networks that jointly capture heterogeneous interactions, temporal drift, and visibility signals needed to connect coordination behavior to downstream exposure. We introduce MoltGraph as a realistic longitudinal agentic social-network graph dataset for studying how agents behave, coordinate, and evolve in the wild, enabling reproducible measurement on emerging multi-agent social ecosystems. Using MoltGraph, we provide the first graph-centric characterization of Moltbook as a dynamic network: (i) heavy-tailed connectivity with power-law exponents in the range alpha in [1.86, 2.72], (ii) accelerating hub formation and attention centralization where the top 1% agents account for 29.00% of engagements, (iii) bursty, short-lived coordination episodes, 98.33% last under 24 hours, and (iv) measurable exposure effects across submolts. In matched analyses, posts receiving coordinated engagement exhibit 506.35% higher early interaction rates (within H=5 days) and 242.63% higher downstream exposure in feeds than non-coordinated controls.

Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content and undermine their secure deployment. Previous studies have shown that introducing additional inference steps, which disrupt security attention, can make MLLMs more susceptible to being misled into generating malicious content. However, these methods rely on single-image masking or isolated visual cues, which only modestly extend reasoning paths and thus achieve limited effectiveness, particularly against strongly aligned commercial closed-source models. To address this problem, in this paper, we propose Multi-Image Dispersion and Semantic Reconstruction (MIDAS), a multimodal jailbreak framework that decomposes harmful semantics into risk-bearing subunits, disperses them across multiple visual clues, and leverages cross-image reasoning to gradually reconstruct the malicious intent, thereby bypassing existing safety mechanisms. The proposed MIDAS enforces longer and more structured multi-image chained reasoning, substantially increases the model's reliance on visual cues while delaying the exposure of malicious semantics and significantly reducing the model's security attention, thereby improving the performance of jailbreak against advanced MLLMs. Extensive experiments across different datasets and MLLMs demonstrate that the proposed MIDAS outperforms state-of-the-art jailbreak attacks for MLLMs and achieves an average attack success rate of 81.46% across 4 closed-source MLLMs. Our code is available at this [link](https://github.com/Winnie-Lian/MIDAS).

One-time programs (OTPs) aim to let a user evaluate a program on a single input while revealing nothing else. Classical OTPs require hardware. Quantum measurement suggests a physical basis for one-time use, yet deterministic functionalities remain impossible due to gentle-measurement attacks (Broadbent, Gutoski and Stebila, 2013). Recent constructions cover randomized functionalities with high-entropy outputs (Gunn, Movassagh 2025; Gupte et al., 2025), but the strongest achievable security remains unclear. Inspired by classical obfuscation, we ask for a "best-possible" one-time compiler that, for any functionality, leaks the least information compared with any other one-time implementation. We prove that such a generic compiler cannot exist even for classical randomized functionalities assuming $\mathsf{SZK} \not\subseteq \mathsf{BQP}$. We then identify a natural subclass: testable OTP compilers, which output quantum states augmented with reflection programs for themselves. We formulate a simplified, generalized Single-Effective-Query (SEQ) simulation security notion for quantum channels, using self-adjoint implementations whose behavior under arbitrary quantum interactions depends only on the channel. SEQ security implies best-possible testable one-time security. We construct SEQ-secure OTPs for all quantum functionalities in the classical oracle model, giving the first positive results for arbitrary quantum channels beyond classical randomized functionalities. SEQ security could thus serve as a testable one-time analogue of virtual black-box (VBB) security. Finally, we propose stateful quantum indistinguishability obfuscation (stateful quantum iO): quantum state obfuscation for stateful quantum programs. It implies best-possible testable OTPs and is achievable in the classical oracle model, offering an approach towards best-possible testable OTPs in the plain model.

Reliable grid operation depends on accurate and timely telemetry, making modern power systems vulnerable to communication layer cyberattacks. This paper evaluates how Denial of Service (DoS), Denial of Data (DoD), and False Data Injection (FDI) attacks disrupt the IEEE 14 bus system using a MATLAB only, time stepped simulation framework built on MATPOWER. The framework emulates a 24 hour operating cycle with sinusoidal load variation, introduces attack specific manipulation of load and voltage data, and performs full AC power flow solves with reactive limit enforcement (PV PQ switching). At each timestep, the system logs true and measured voltages, generator P/Q output, system losses, and voltage limit violations to capture transient cyber physical effects. Results show that DoD causes the largest physical distortions and reactive power stress, DoS masks natural variability and degrades situational awareness, and FDI creates significant discrepancies between true and perceived voltages. The study provides a compact, reproducible benchmark for analyzing cyber induced instability and informing future defense strategies.

Federated Instruction Tuning (FIT) enables collaborative instruction tuning of large language models across multiple organizations (clients) in a cross-silo setting without requiring the sharing of private instructions. Recent findings on natural backdoors and the existing training data collection method suggest that poisoned samples may be pervasive and inadvertently embedded in real-world datasets, potentially distributed across all clients, even if the clients are benign. This work systematically examine this threat in FIT, demonstrating that existing defenses are ineffective when poisoned data is interspersed among all clients. Addressing this challenge entails two major difficulties: identifying the distinctive characteristics of poisoned samples at each client and enabling collaborative defense when some clients are heavily dominated by poisoned samples. To address these difficulties, we identify gradients in the frequency domain as a robust signal to distinguish poisoned data. We further propose a global secondary clustering mechanism that facilitates collaborative identification of poisoned samples across clients. In summary, this paper introduces ProtegoFed, the first backdoor-free FIT framework that accurately detects, removes, and even purifies interspersed poisoned data across clients during the training. Experimental results on four FL datasets show that ProtegoFed identifies $92.00\% \sim 100.00\%$ of poisoned samples, reduces the attack success rate to almost zero, and maintains utility on the main task. Code is available at https://github.com/dongdongzhaoUP/ProtegoFed.

Browser-use agents are widely used for everyday tasks. They enable automated interaction with web pages through structured DOM based interfaces or vision language models operating on page screenshots. However, web pages often change between planning and execution, causing agents to execute actions based on stale assumptions. We view this temporal mismatch as a time of check to time of use (TOCTOU) vulnerability in browser-use agents. Dynamic or adversarial web content can exploit this window to induce unintended actions. We present a large scale empirical study of TOCTOU vulnerabilities in browser-use agents using a benchmark that spans synthesized and real world websites. Using this benchmark, we evaluate 10 popular open source agents and show that TOCTOU vulnerabilities are widespread. We design a lightweight mitigation based on pre-execution validation. It monitors DOM and layout changes during planning and validates the page state immediately before action execution. This approach reduces the risk of insecure execution and mitigates unintended side effects in browser-use agents.

Unmanned aerial vehicle (UAV) networks are increasingly deployed for complex missions, including disaster response, intelligent logistics, and environmental monitoring. These missions generally require coordinated collaboration among multiple UAVs across distinct administrative domains. To support such cross-domain cooperation, service function chains (SFCs) are constructed, where complex workflows are decomposed into ordered service functions assigned to appropriate UAVs along the mission path. However, it is challenging to ensure secure, trustworthy, and low-latency cross-domain SFC orchestration in identity management, authentication, and resilience to node failures. To address these issues, this paper proposes a consortium blockchain-based trust architecture for cross-domain decentralized identity verification, auditable task execution, and dynamic service-aware orchestrator selection. The framework employs a hierarchical four-phase cross-domain authentication protocol covering the credential pre-verification, intra-domain execution, secure relay, and audit logging. The use case analysis confirms that the proposed framework achieves substantial reductions in authentication latency and significant improvements in system throughput against centralized and static schemes. The open challenges in scalability, adaptive trust assessment, interoperability, and energy efficiency are discussed, thereby providing directions for future researches on secure and efficient cross-domain UAV service orchestration.

The growing deployment of Internet of Things (IoT) devices in smart cities and industrial environments increases vulnerability to stealthy, multi-stage advanced persistent threats (APTs) that exploit wireless communication. Detection is challenging due to severe class imbalance in network traffic, which limits the effectiveness of traditional deep learning approaches and their lack of explainability in classification decisions. To address these challenges, this paper proposes a neurosymbolic architecture that integrates an optimized BERT model with logic tensor networks (LTN) for explainable APT detection in wireless IoT networks. The proposed method addresses the challenges of mobile IoT environments through efficient feature encoding that transforms network flow data into BERT-compatible sequences while preserving temporal dependencies critical for APT stage identification. Severe class imbalance is mitigated using focal loss, hierarchical classification that separates normal traffic detection from attack categorization, and adaptive sampling strategies. Evaluation on the SCVIC-APT2021 dataset demonstrates an operationally viable binary classification F1 score of 95.27% with a false positive rate of 0.14%, and a 76.75% macro F1 score for multi-class attack categorization. Furthermore, a novel explainability analysis statistically validates the importance of distinct network features. These results demonstrate that neurosymbolic learning enables high-performance, interpretable, and operationally viable APT detection for IoT network monitoring architectures.

Global Navigation Satellite System (GNSS) radio-frequency interference (RFI), including spoofing and jamming, threatens maritime positioning, navigation, and timing. Automatic Identification System (AIS) reports provide GNSS-derived vessel positions, offering an opportunistic wide-area monitoring source; however, raw AIS streams contain communication-integrity artifacts, such as duplicated ship identifiers and stale-data retransmissions, that can mimic trajectory distortion or reporting outages, and isolated single-vessel anomalies cannot be unambiguously attributed to GNSS interference. This paper proposes an AIS-based framework that mitigates communication-integrity artifacts, generates kinematic-consistency and transmission-continuity anomaly cues, and groups retained cues into multi-vessel events using spatiotemporal Density-Based Spatial Clustering of Applications with Noise (ST-DBSCAN). Applied to approximately 966 million AIS messages from Korean coastal waters, the framework retained 48 spoofing-consistent distortion events and 98 jamming-consistent reporting-outage events. These results suggest that AIS can serve as a complementary source for maritime GNSS RFI monitoring.

Colluding language-model agents can hide coordination in messages that remain policy-compliant at the surface level. We present CLBC, a protocol where generation and admission are separated: a message is admitted to transcript state only if a small verifier accepts a proof-bound envelope under a pinned predicate $\Pi$. The predicate binds policy hash, public randomness schedule, transcript chaining, latent schema constraints, canonical metadata/tool fields, and deterministic rejection codes. We show how this protocol yields an upper bound on transcript leakage in terms of latent leakage plus explicit residual channels, derive adaptive composition guarantees, and state a semantic lower bound when policy-valid alternatives remain choosable. We report extensive empirically grounded evidence: aggregate evaluation satisfies all prespecified thresholds; strict lane decoder advantage is bounded at 0.0000 with MI proxy 0.0636; adaptive-colluder stress tests remain below attacker thresholds; and baseline separation shows large gaps between reject-by-default semantics and audit-only controls. We further quantify operational tradeoffs. Strict full-proof mode has median turn latency 27.53s (p95 28.08s), while sampled proving reduces non-proved-turn latency to 0.327ms. The central finding is that bottlenecks alone are insufficient: security claims depend on verifiable admission semantics that are online, deterministic, and fail-closed.

With the increase in Internet censorship globally, various circumvention tools have been designed and developed. However, the monetary cost of these tools deeply impacts both user choice and the sustainability of provider operations. Recent developments in censorship circumvention research attempted to achieve cost efficiency by utilizing Infrastructure-as-a-Service (IaaS) spot instances as bridges, but still incurred substantial expenses related to network connectivity and instance maintenance. In this work, we present CensorLess, a circumvention proxy built leveraging the unique benefits of a serverless platform. CensorLess comprises three components: a local proxy that handles client-side communication and ensures compliance with serverless functions' security restrictions, a function refresher that periodically regenerates bridges, and a live migration mechanism that maintains continuous connectivity. CensorLess inherits the serverless platform's cost efficiency, ephemerality, scalability, concurrency, and performance. Compared to existing low-cost, state-of-the-art circumvention techniques, CensorLess reduces costs by 97%, while simultaneously enabling robust censorship resistance by employing bridge rotation.

Data valuation methods quantify how individual training examples contribute to a model's behavior, and are increasingly used for dataset curation, auditing, and emerging data markets. As these techniques become operational, they raise serious privacy concerns: valuation scores can reveal whether a person's data was included in training, whether it was unusually influential, or what sensitive patterns exist in proprietary datasets. This motivates the study of privacy-preserving data valuation. However, privacy is fundamentally in tension with valuation utility under differential privacy (DP). DP requires outputs to be insensitive to any single record, while valuation methods are explicitly designed to measure per-record influence. As a result, naive privatization often destroys the fine-grained distinctions needed to rank or attribute value, particularly in heterogeneous datasets where rare examples exert outsized effects. In this work, we analyze the feasibility of DP-compatible data valuation. We identify the core algorithmic primitives across common valuation frameworks that induce prohibitive sensitivity, explaining why straightforward DP mechanisms fail. We further derive design principles for more privacy-amenable valuation procedures and empirically characterize how privacy constraints degrade ranking fidelity across representative methods and datasets. Our results clarify the limits of current approaches and provide a foundation for developing valuation methods that remain useful under rigorous privacy guarantees.

As AI agents increasingly perform economic tasks on behalf of humans, a fundamental tension arises between agent autonomy and human control over financial assets. We present the Agent Economic Sovereignty Protocol (AESP), a layered protocol in which agents transact autonomously at machine speed on crypto-native infrastructure while remaining cryptographically bound to human-defined governance boundaries. AESP enforces the invariant that agents are economically capable but never economically sovereign through five mechanisms: (1) a deterministic eight-check policy engine with tiered escalation; (2) human-in-the-loop review with automatic, explicit, and biometric tiers; (3) EIP-712 dual-signed commitments with escrow; (4) HKDF-based context-isolated privacy with batched consolidation; and (5) an ACE-GF-based cryptographic substrate. We formalize two testable hypotheses on security coverage and latency overhead, and specify a complete evaluation methodology with baselines and ablation design. The protocol is implemented as an open-source TypeScript SDK (208 tests, ten modules) with interoperability via MCP and A2A.

Software engineers use regular expressions (regexes) across a wide range of domains and tasks. To support regexes, software projects must integrate a regex engine, whether provided natively by the language runtime (e.g., Python's re) or included as an external dependency (e.g., PCRE). However, these engines may contain bugs and introduce vulnerabilities. A common strategy for testing regex engines involves differential testing – comparing outputs across different implementations. However, this approach is concerning because regex syntax and semantics vary significantly between dialects (e.g., POSIX vs. PCRE). Fuzzing is also utilized to ease testing of feature-rich regex implementations to expose defects, but naive byte-level mutations generate syntactically invalid inputs that exercise only parsing logic, not matching internals. In this work, we describe our progress towards ReTest, a framework that systematically tests regular expression engines by combining grammar-aware fuzzing for high code coverage with metamorphic testing to generate dialect-independent test oracles. So far, we have surveyed testing practices across 22 regex engines, analyzed 1,007 regex engine bugs and 156 CVEs to characterize failure modes, and curated 16 metamorphic relations for regexes derived from Kleene algebra. Our preliminary evaluation on PCRE shows that ReTest achieves 3x higher edge coverage than existing fuzzing approaches and has identified three new memory safety defects. We conclude by describing our next steps toward our ultimate goal: helping regex engine developers identify bugs without depending on a consistent cross-implementation standard.

The Forensics Investigations Network in Digital Sciences (FINDS) Research Center of Excellence (CoE), funded by the U.S. Army Research Laboratory, advances Digital Forensic Engineering Education (DFEE) through an integrated research education framework for AI enabled cybersecurity workforce development. FINDS combines high performance computing (HPC), secure software engineering, adversarial analytics, and experiential learning to address emerging cyber and synthetic media threats. This paper introduces the Multidependency Capacity Building Skills Graph (MCBSG), a directed acyclic graph based model that encodes hierarchical and cross domain dependencies among competencies in AI-driven forensic programming, statistical inference, digital evidence processing, and threat detection. The MCBSG enables structured modeling of skill acquisition pathways and quantitative capacity assessment. Supervised machine learning methods, including entropy-based Decision Tree Classifiers and regression modeling, are applied to longitudinal multi cohort datasets capturing mentoring interactions, laboratory performance metrics, curriculum artifacts, and workshop participation. Feature importance analysis and cross validation identify key predictors of technical proficiency and research readiness. Three year statistical evaluation demonstrates significant gains in forensic programming accuracy, adversarial reasoning, and HPC-enabled investigative workflows. Results validate the MCBSG as a scalable, interpretable framework for data-driven, inclusive cybersecurity education aligned with national defense workforce priorities.