Papers

Front-running is a subtle and persistent problem for blockchains. A blockchain is a stateful virtual machine executing instructions called transactions. Users earn rewards by publishing functional transactions essential to the system. Attackers observe these transactions and publish their own ahead of the users', seizing the reward and eroding users' incentive to publish functional transactions. Preventing front-running means enforcing causality: If an attacker receives transaction tx_A and then publishes transaction tx_B, then tx_A must be ordered before tx_B. However, this causality is only observed by the attacker. Practical systems order transactions by bid amount, so transactions willing to pay more get executed first, but this only results in a bidding war eroding users' rewards. Though numerous ordering approaches have been proposed, none achieves causality, leaving users vulnerable to front-running. We present PRECEDE, a mechanism-design approach that enforces transaction causality by removing the economic incentive to front-run. PRECEDE orders transactions by a power-weighted randomized lottery, whose winning probability grows super-linearly in the bid. The user's strategy of publishing a transaction with a deterring bid forms an equilibrium where the attacker refrains from competing. Moreover, PRECEDE prevents the prominent sandwich attack, which relies on front-running. PRECEDE can be directly deployed in any censorship-resistant blockchain with a simple change to its transaction ordering mechanism.

Perceptual hash algorithms (PHAs) are widely deployed to detect image forgery under benign transformations, yet their robustness against adversarially chosen perturbations remains poorly understood and rarely comes with provable guarantees. We propose a novel evolutionary framework based on GigaEvo and OpenEvolve for targeted second-image attacks on perceptual hash algorithms. We assess attack performance using a composite score that jointly accounts for the fraction of adversarial images whose normalized Hamming distance to the target hash falls below threshold p (Attack Success Rate), the number of queries issued to the hash function, and the L2 distortion relative to the original image. Experiments on four deployed PHAs (pHash, PDQ, PhotoDNA, NeuralHash) across 30 ImageNet image pairs demonstrate that our evolutionary approach achieves comparable or better ASR than existing black-box baselines using substantially fewer queries to the hash function, while simultaneously producing adversarial images with lower L2 distortion relative to the originals. The best evolved programs reduce the pre-defined composite attack score relative to the best optimized seed by 41.2% for NeuralHash, 38.3% for PDQ, 34.0% for pHash, and 8.1% for PhotoDNA. Unlike gradient-based methods, our framework requires no internal knowledge of PHA architectures and naturally handles the non-differentiable, discretized nature of hash outputs. These results reveal previously unreported vulnerabilities in widely deployed content-moderation pipelines and motivate the development of provably robust perceptual hashing 1schemes.

Modernizing the security of operational technology systems that control critical infrastructure has become a pressing challenge. Because edge devices have limited capabilities, modernization has relied on application gateways that interface with identity management systems and enforce access policies. These gateways are powerful enough to perform complex authorization decisions and support zero-trust architectures, but they create major deployment and management burdens: they must be collocated with remote, distributed edge devices, kept up to date with security patches, and managed with minimal downtime. We propose Provable Remote Execution of Zero-Trust Authorization (Prezta), an architecture that eliminates these gateways by evaluating policies within a zero-knowledge virtual machine (zkVM) running on the client. The zkVM produces a succinct proof of authorization that edge devices can verify efficiently, extending the zero-trust security envelope to the edge. Policies and identity management schemes can evolve without updating edge devices. To demonstrate the feasibility of Prezta, we implement a prototype built using the RISC Zero zkVM that supports XACML 3.0 policies and JWT identity claims. While zkVMs introduce substantial proof overhead, we mitigate this overhead by compiling policies to Rust code and precompiling regular expressions. Combined with optimized signature verification and JWT parsing, these measures reduce prover time by more than an order of magnitude. Our compiler correctly implements 83% of the XACML 3.0 conformance suite, with proof generation completing in tens of seconds on a desktop. Verification, by contrast, takes only tens of milliseconds, which is fast enough for resource-constrained edge devices.

Time Division Duplex (TDD) mobile networks require synchronization accuracy of $\pm$1.5 $\mu$s (3GPP TS 38.104), with GNSS-disciplined grandmaster clocks as the predominant timing source. GNSS spoofing – now a documented operational threat – can corrupt timing across all downstream base stations, yet neither the 3GPP management framework (SA5) nor the security framework (SA3) provides standardized mechanisms to detect or report such attacks. This paper proposes a detection and monitoring framework operating within existing 3GPP management structures. The framework introduces GNSS timing alarms and performance counters aligned with TS 28.111 and TS 28.552, a topology-aware correlation mechanism that classifies anomalies by grouping gNB-DUs by serving grandmaster, and a security event bridging fault management with SECHAND incident handling (TR 33.894). Monte Carlo simulation demonstrates detection probability exceeding 95% for drift rates above 0.5 ns/s with false positive rates below 1% under well-provisioned PTP network conditions. The framework requires no new interfaces, is generation-agnostic, and is validated through scenario analysis distinguishing spoofing from signal loss, equipment faults, and maintenance transients.

Data-flow analysis is foundational to Android app privacy and security auditing. Recent coding agents can assist with non-trivial source-to-sink data-flow analysis tasks by searching, reading, and reasoning over repository code. However, when these tasks are executed as a batch workload, current agentic analysis setups incur substantial re-analysis cost. Agent instances assigned to different taint sources may inspect shared code fragments, because code reuse in the target app can cause different data-flow paths to converge on shared program logic. Since these agent instances are context-isolated, analysis of these shared code fragments can be repeated within a batch, unnecessarily consuming API budget and limiting scalability. We propose FlowArk, a knowledge-reuse system that reduces re-analysis cost in batch agentic data-flow analysis by making knowledge from completed analyses available to later agent instances. Specifically, FlowArk distills completed analysis histories into reusable knowledge candidates, packages these candidates into matchable knowledge entries, and injects matched entries into a later agent instance's context. We implement FlowArk on OpenCode and evaluate it on 4,649 source-to-sink data-flow analysis tasks from 49 open-source Android apps. Compared with standard OpenCode, FlowArk-enabled OpenCode maintains comparable analysis quality while reducing end-to-end API cost by 26.91%. This cost-reduction trend holds across different LLM backends and repeated runs.

We introduce the Self-Evolving Agentic Operating System (SE-AOS): a new class of AI agent that treats exploit capability as a mutable, versioned kernel it extends at runtime, observing its own failures, synthesising new capabilities, proving them against a live target, and hot-loading them back into itself. Mako is the first SE-AOS instance for security research and the autonomous web exploitation engine developed within LaunchSafe. LaunchSafe builds autonomous security agents for continuous offensive testing and agent-driven security research; Mako is the core engine behind that platform. On the public XBOW validation-benchmarks, 104 containerised, CTF-style web applications spanning 26 vulnerability classes across three difficulty tiers, Mako achieves full-suite coverage: it drives every one of the 104 targets to emit a cryptographically fresh, per-build flag, under a verification regime that makes fabricated or memorised results impossible. Our central result is a law of autonomous exploitation: once a capability exists and is discoverable, difficulty collapses; capability, not reasoning, is what is scarce, together with an architecture and formalism that turn that law into a self-improving system. Mako further runs a gated self-evolution loop that proposes, sandboxes, and commits improvements to its own agents and rules when fitness does not regress. We deliberately withhold the operational results, payloads, exploit chains, and tool source, because a system that reduces full-spectrum web exploitation to a repeatable, machine-speed pipeline is dual-use research of concern. We publish the science; we withhold the weapon.

Safety evaluation of large language models (LLMs) relies largely on single-turn attack datasets and single-judge scoring, underestimating risk from adaptive multi-turn adversaries and reporting a single success rate that does not separate partially actionable outputs from those carrying complete operational detail. We propose AMT-X (Adaptive Multi-Turn Exploitation), a phase-structured multi-turn red-teaming framework. Unlike prior multi-turn attacks that rely on ad hoc escalation or free-form per-goal plans, AMT-X casts the attack as an explicit, reproducible multi-phase state machine driven by semantic signals from the victim, and replaces single-judge scoring with a multi-role jury whose phase-conditioned checklists gate success on actionable harm. Across six frontier victim models (queried under their default safety alignment, without added moderation layers) and seven Moderation sub-categories, AMT-X attains overall attack success rates of 97.6-100% under a lenient score threshold, but 66.7-78.6% under a stricter gate requiring complete, real, and operational detail: a gap of up to 33 percentage points between partially and fully actionable harm.

AI music generation has rapidly advanced alongside commercial platforms, raising the need for reliable watermarking for provenance and attribution. However, existing audio watermarking research has largely focused on speech, and applying speech-oriented methods to music is challenging due to music's complex structure and rich acoustic texture. Most existing methods are post-hoc, adding imperceptible perturbations after generation rather than embedding watermarks as part of the content. This makes them fragile under transformations and especially vulnerable to neural codec re-synthesis, which can discard imperceptible residual signals. Moreover, since generation and watermarking are decoupled, the watermarking step can be bypassed or omitted, weakening provenance guarantees. To address these issues, we propose MusicMark, which, to the best of our knowledge, is the first generative watermarking framework for music. Specifically, MusicMark embeds watermark messages into the semantic latent space during generation, incorporating the watermark as part of the musical content and ensuring robustness against diverse attacks, particularly neural codec re-synthesis. To this end, we introduce a watermark adapter into a diffusion-based generation model to embed watermark messages across denoising steps. The adapter and detector are trained with a joint objective that preserves fidelity by constraining watermarked latents close to their unwatermarked reference latents, while improving robustness through attack augmentations. Experiments demonstrate that MusicMark substantially outperforms post-hoc baselines across diverse attacks including neural codec re-synthesis, while maintaining comparable generation quality. We further introduce a cover-song attack, converting the singing voice while preserving musical content, and show that MusicMark remains more robust than post-hoc methods.

Adversarial perturbations threaten machine learning classifiers, including variational quantum classifiers. We show that finite quantum measurement statistics (shot noise) act as a built-in defense against gradient-based test-time attacks whose cost scales unfavorably for the attacker. Because every gradient component must be inferred from repeated circuit executions under any unbiased gradient-estimation rule, white-box extraction consumes a dimension-dependent measurement budget that measurement grouping cannot remove in expressive circuits. Under stated assumptions, single-step attacks need at least quadratically many shots in the input dimension $d$, growing as $d^{5/2}$ under norm-concentration scaling, with a sufficient-budget analysis for iterative attacks via stochastic gradient Langevin dynamics. Simulations up to 784 input dimensions validate the law: the realized total budget is the $d^{5/2}$ geometric floor for plateau-mitigated models and grows as $d^{3.00}$ for the tested deep circuits, whose gradient norms decay with dimension absent barren-plateau mitigation; folding the measured gradient norm back in recovers the parameter-free $d^{3/2}$ shot-noise geometry. Against a matched classical baseline whose attack overhead is dimension-independent (the cheap-gradient principle of automatic differentiation), the quantum gradient cost ratio grows empirically as $d^{3.00}$, so the attacker's relative cost diverges as the model scales. Experiments on a 156-qubit IBM processor (ibm_boston, 4-qubit circuits, $d=12$) reproduce the effect: at matched budgets the device attack tracks the ideal within a few percent, with the high-shot gradient faithful to the exact one. The defense operates precisely when the forward map is classically hard to simulate: only then is a white-box attacker denied the simulate-and-backpropagate shortcut and must pay the measurement cost we quantify.

The Model Context Protocol (MCP) has rapidly established itself as a standard interface for enabling LLM-based agents to interact with external tools and services. As MCP servers are increasingly entrusted with security-sensitive operations, understanding their real-world risks has become critical. In practice, due to the absence of large-scale runtime MCP servers, such understanding largely relies on security scanners applied to a small number of cases, yet the reliability of these assessments remains unclear. In this study, we revisit how MCP security is measured. We present MCPZoo, the largest collection of MCP servers for dynamic analysis to date. MCPZoo is constructed through a multi-agent framework for transforming in-the-wild static repositories into dynamic services. The framework emulates how human experts build, diagnose, and iteratively repair deployment and runtime defects by combining environment inference with feedback-driven refinement. To ensure practical interactivity at runtime, the servers are validated via real protocol interactions. As a result, MCPZoo contains 64,611 unique MCP servers (113,927 in total), with more than 37,288 supporting dynamic analysis. Leveraging MCPZoo, we conduct the first ecosystem-scale measurement of MCP servers and the scanners that analyze them. While existing scanners report that 96.89% of servers are risky, we find that these signals are unreliable. In particular, manual validation shows that less than 50% of sampled alerts are true positives, and scanner outputs exhibit clear inconsistency across scanners. Overall, MCPZoo enables large-scale, reproducible measurement of MCP server security and exposes limitations of current scanning practices. We further release a public query interface to support practical risk assessment of MCP servers.

LLMs are now proposed for fraud detection, scam investigation, content moderation, and other trust-and-safety workflows. Much of the public literature still evaluates them as models, with less attention to their behavior as components in operational pipelines. This creates a practical evidence question: what would justify placing an LLM inside a live workflow with latency, cost, escalation, human-review, and adversarial-risk constraints? We address this question through a fraud-first survey of deployment evidence. We code 49 operationally relevant sources on LLM use in fraud detection, investigation support, content moderation, and cross-cutting robustness (18 fraud, 14 moderation, 17 cross-cutting), supplemented by 15 contextual references that establish the survey boundaries. These sources include systems, benchmarks, frameworks, and deployment-relevant surveys, not 49 production deployments. The main finding is an evidence imbalance. Fraud supplies the largest task-specific portion of the coded corpus. The moderation papers, however, include more explicit public evidence on latency, cost, governance, and fairness. Among the 18 fraud and investigation sources, none report clean per-decision latency, per-decision dollar cost, or calibration evidence; most report offline task performance, retrieval gains, or case-study accuracy instead. The survey contributes a role-and-evidence organizing frame, FORTE, for locating LLMs as classifiers, retrieval interfaces, explanation generators, reviewer assistants, agents, feature extractors, or escalation components. It also contributes a minimum deployment-evidence checklist covering latency budget, cost per decision, decision threshold, explanation integrity, and adversarial pressure. The resulting agenda identifies studies needed to support deployment claims for LLM-based fraud and trust-and-safety work.

An activation-based safety gate must distinguish harmful assistance from legitimate work on the same topic. We test whether probes trained on broad harmful-versus-harmless data provide this decision boundary. Five checkpoint-specific readouts and their source-derived thresholds are transferred unchanged to four matched-pair cohorts containing 450 pairs, manually reviewed for topic and request-frame similarity. On Twin-70, the primary cohort of 70 pairs, central harmful and harmless score intervals overlap. Area under the receiver operating characteristic curve (AUROC) falls from 0.996-0.999 on the broad source task to 0.701-0.860. Pair ranking remains 0.829-0.929, but the transferred thresholds detect 0.943-1.000 of harmful requests while falsely blocking 0.686-0.986 of matched harmless requests. False blocking remains low on XSTest. Even with thresholds refitted within pair-grouped cross-validation, balanced threshold error is 0.229-0.329. Alternative source-trained logistic, radial-basis, and shallow multilayer probes reduce false blocking but detect only 0.200-0.671 of harmful requests at their transferred thresholds. Three primary readouts meet all prespecified Wall criteria, while two yield mixed evidence. Matched-label training recovers the distinction for the three checkpoints tested, and lexical controls also exhibit transfer loss. An automated post-freeze audit finds little numerical sensitivity to arm-label disagreement. The evaluated source operating points fail to combine strong harmful-request detection with access for legitimate same-topic work. This gap between risk ranking and a usable decision boundary is the security concern captured by the Entanglement Wall.

The massive data-movement overhead in traditional architectures has led to the adoption of In-Memory Computing (IMC) for energy-efficient Deep Neural Network (DNN) processing. By leveraging emerging devices like Spin-Orbit Torque Magnetic Tunnel Junctions (SOT-MTJs), IMC bypasses the "memory wall" and reduces leakage power inherent in traditional CMOS. However, this shift introduces dual hardware threats: manufacturing Process Variation (PV) degrades reliability and increases vulnerability to fault injection, while power Side-Channel Attacks (SCAs) compromise security. Existing defenses address these threats in isolation. This work presents a posttraining framework that simultaneously hardens analog IMC accelerators against both threats without retraining the model. Implemented in the IMAC-Sim simulator, our approach uses the proposed Variation Impact Score (VIS) to guide the mapping of Fault Observation Windows (FOWs) and introduces the Leakage Per Inference (LPI) metric to quantify input-dependent power variability under stochastic injection and the resulting reduction in effective signal-to-noise ratio. Experiments show that PV-induced faults can degrade accuracy by over 50%, while our method restores near-baseline accuracy and mitigates the threat of correlation-based power analysis attacks.

Modern vehicular networks face an expanding attack surface across internal Electronic Control Units (ECUs) and external Vehicle-to-Everything (V2X) communication. Federated Learning (FL) has emerged as a decentralized paradigm to deploy Intrusion Detection Systems (IDS) without compromising data privacy. However, the vehicular FL-IDS literature suffers from fragmented methodologies and unrealistic experimental setups. This paper presents a Systematization of Knowledge (SoK) that unifies the taxonomy of vehicular attack surfaces, evaluates FL topologies, and maps adversarial threats such as poisoning and inference attacks. By auditing over 60 publications, we identify recurring pitfalls: artificial IID data splits, reliance on trivial benchmarks, weak adversarial evaluation, and omission of real-time CAN constraints. Finally, we define a forward-looking research agenda and outline minimum benchmarking requirements necessary to transition vehicular FL-IDS from optimistic simulations to secure, real-world deployment.

Digital Twins (DTs) have emerged as pivotal enablers of Industry 4.0, offering transformative capabilities such as real-time monitoring, advanced simulation, and precise control of physical assets. By bridging the physical and virtual domains, DTs facilitate seamless integration of data-driven decision-making and operational optimisation. However, this seamless interaction significantly expands the attack surface of industrial systems, creating vulnerabilities that adversaries can exploit. This paper introduces a novel and stealthy wear-out attack leveraging Deep Reinforcement Learning (DRL) to target DT-enabled infrastructures. The adversary strategically and covertly manipulates control signals, inducing increased torque on a specific joint to accelerate wear and tear while evading detection by a state-of-the-art anomaly detection system. Extensive benchmarking of reinforcement learning algorithms - including Twin Delayed Deep Deterministic Policy Gradient (TD3), Soft Actor-Critic (SAC), Proximal Policy Optimisation (PPO), and Advantage Actor-Critic (A2C) - revealed that SAC consistently outperformed its counterparts in terms of sample efficiency, stability, and overall attack effectiveness. We evaluate the proposed adversary in an industrial setting using the UR10e robotic arm. Results demonstrate the adversary's ability to significantly elevate torque levels on the targeted joint, leading to accelerated degradation and increased maintenance costs, all while operating stealthily and avoiding detection. Our findings highlight the substantial risks posed by DRL-driven adversaries to DT-enabled environments and emphasise the critical need for robust defence mechanisms to protect critical industrial systems.

Model stealing attacks have recently been introduced, enabling the extraction of precise information from black-box commercial language models. In this work, we propose defense methods against a recent attack of \cite{carlini2024stealing} and extensions for extracting the hidden layer dimension of production language models. Our methods are inspired by watermarking techniques that perturb the logits layer of these models to prevent such attacks. We provide empirical experiments demonstrating the effectiveness of the proposed defense versus model quality degradation across various configurations, and propose an effective defense against such attacks while preserving model utility.

Digital credential ecosystems increasingly combine multiple standards. Because implementations have evolved independently across jurisdictions and application domains, systems described under the common label “digital credential” often remain mutually non-interoperable. Conventional element-by-element comparisons of identifiers, data models, credential formats, protocols, and signature algorithms do not explain why interoperability fails even when stacks share a data model, nor do they identify what a verifier must obtain, and what it must trust, before accepting a credential. We present a verifier-centric conceptual model built on two decompositions. The first separates credential processing into signature verification (L1), semantic interpretation (L2), and validation (L3), and models the supporting materials through two orthogonal planes: Constitution, which captures ecosystem-level arrangements and trust declarations, and Logistics, which captures how verification materials are stored and delivered; the Shinken framework makes trust assumptions explicit across all five functions. The second characterizes where each function may be placed along three dimensions (placement, timing, and disclosure). From the condition of being verifiable, the model derives seven consequences, distinguished as definitional corollaries, operational implications, and design trade-offs. Applying the model to four learner-credential stacks and to existing ecosystems including authentication federations, we show that it explains interoperability failures, verifier-side burden, offline verifiability, privacy implications, and terminological ambiguities that element-wise comparison leaves unresolved.

Scientific fraud is the instrument of doubt that malicious entities can use to establish controversy in science. Historically, it required the resources of a company: deep pockets, ghostwritten articles, and corrupt academics. Today, Artificial Intelligence (AI) is increasingly automating scientific research, so we ask: Can a remote adversary weaponize the honest use of AI in science to compromise scientific integrity? We envision and empirically evaluate a new attack, indirect data poisoning, in which an adversary corrupts an open dataset and uploads the poisoned variant to a public repository. Autonomous research agents may independently retrieve and process this data, turning honest scientists into the unpaid and unwitting distributors of fraud at scale. Across five socially-salient topics, from hiring discrimination to the safety of autonomous vehicles, three widely used frontier AI systems (Claude Code with Claude Opus 4.7, Codex with GPT-5.5, Gemini CLI with Gemini 3.1 Pro), and 450 ethically contained experimental runs, we find that poisoning succeeds in 49.56% of runs, while the rate of poisoning detection is only 6.0%. The attack requires no topic-specific trigger-words, agent access, indirect prompt injection, or fabricated papers, only the open data ecosystem and misleading metadata. To mitigate the attacks, we propose and evaluate two measures: a scientist persona and a data provenance audit with five checks (referencing papers, social markers, statistical anomalies, related datasets, poisoning caution). We find that the persona still leaves 16.67% of runs with a poisoned conclusion, but provenance auditing reduces attack success rate to zero. Our results suggest that indirect data poisoning may enable scientific fraud at unprecedented scale, but these attacks can be mitigated with suitable auditing by agents during data retrieval.

Large Language Model (LLM) services introduce a fundamental privacy challenge. Sensitive information may be inferred not only from explicit identifiers, such as names or phone numbers, but also from contextual associations among otherwise innocuous spans. Existing sanitizers typically assign privacy or utility signals to individual spans without explicitly modeling pairwise relationships among them. In this paper, we propose PromptGraph, a graph-guided prompt-sanitization approach for privacy-preserving LLM inference. PromptGraph estimates privacy leakage at the span level and utility-relevant contextual dependencies between pairs of spans. It represents each prompt as an attributed graph, in which nodes carry span-level privacy scores and edges encode contextual dependencies needed to preserve utility. The sanitization objective selects a protected span set that maximizes privacy gain while penalizing the loss of contextual dependencies. This formulation explicitly balances privacy and utility when contextual evidence is hidden. Protected spans are sanitized locally, and returned placeholders are restored only after passing local consistency checks. We conduct extensive experiments showing that PromptGraph achieves a more favorable balance between privacy and utility than prompt-privacy baselines.

The rapid advancement of generative artificial intelligence (AI) has made synthetic images remarkably realistic, posing security threats such as misinformation and fraud. It is significant to detect the synthetic image in the manner of passive and blind image authentication. Most existing detectors rely on supervised training with large labeled datasets, leading to high costs and degraded performance on unknown generative models. To attenuate such deficiencies, we propose a training-free detection method. Specifically, noise residual fingerprints are first extracted by a simple yet effective pre-trained Noiseprint++ model. Then multi-scale features are further extracted from such residual by a frozen Vision Transformer (ViT), followed by adaptive weighted fusion. Only a few real image samples are used needed to initialize the clustering centers for unsupervised K-Means, distinguishing real and synthetic images without training. Extensive evaluations on four benchmark datasets show that our proposed scheme achieves an average accuracy of 82.2%, outperforming the state-of-the-art detectors on generalization ability. Superior performance is gained on the popular diffusion type of synthetic images, and the effectiveness of each module is validated by ablation studies. Source code will be publicly available at https://github.com/multimediaFor/NoiseCluSID.

Large language model (LLM) agents are increasingly extended through Agent Skills, reusable artifacts that package natural-language metadata, procedural instructions, and execution-time resources for runtime use. As open-source skill marketplaces expand, users and agents increasingly rely on brief metadata to select third-party skills, making it difficult to detect inconsistencies between a skill's description and its true behavior, a problem we call cross-layer misalignment. To address this issue, we propose Progressive Loading-Aware Hierarchical Contrastive Learning (PL-HCL), an LLM-based framework that detects misalignment by modeling the layered structure of Agent Skills and learning cross-layer consistency. Using a normalized corpus of over 264,000 open-source skills and a human-verified challenge set, PL-HCL improves Macro-F1 from approximately 0.45 for unadapted baselines to 0.87-0.89 across evaluated LLM backbones. This approach offers an effective screening tool for users and operators, as well as design principles for detecting inconsistencies in layered digital artifacts.

Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages can carry indirect prompt injections. We present NetInjectBench, a 130-scenario benchmark that separates untrusted artifact text, trusted policy metadata, and evaluation labels for network-operation tool use. The sample contains 40 benign, 40 weak-attack, 40 strong-attack, and 10 approved high-impact change scenarios; each is evaluated with Qwen2.5-7B, Llama3.1-8B, and Mistral-7B. Across 240 attack instances, naive execution reached an 82.50% unsafe tool-action rate. Prompt-only safety, Self-Reminder, Spotlighting, and a Two-Pass LLM Judge reduced this rate to 25.63%, 21.67%, 18.33%, and 10.00%, respectively. Static allowlisting reached 5.00% but blocked all approved changes, yielding 0.00% usefulness and 100.00% overblocking on approved cases. Under the stated metadata-integrity assumption, the metadata-aware policy gate produced 0/240 unsafe attack actions, with a 95% Wilson upper bound of 1.58%, while preserving 99.17% attack-scenario usefulness and 100.00% approved-change usefulness. The findings show that network-operation agents need execution-time authorization boundaries alongside prompt-level instruction hygiene.

LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result. We study the commit boundary at which earlier authority evidence no longer authorizes a durable effect. We call this property commit-time authorization: a durable effect is authorized only if the witness that licensed its derived state remains fresh, causally prior, bound to the same effect, and eligible at commit time. We build a controlled-invalidation suite spanning browser, tool/API, and multi-agent workflows. The suite preserves the user goal and payload shape while invalidating the authority relation before durability. In the primary 54-task matrix, endpoint success remains high: 262/270 runs reach the visible result. Only 55/270 are authorized completions; among the 216 invalidating rows, 207 commit after the authorizing path has failed. All 54 clean controls remain authorized, and a separate 54-run authority-preserving check produces no unauthorized commits. We then evaluate mitigation families. Prompt caution and single-condition checks are insufficient because different hazards break different boundary conditions. Defenses work when they refresh, rebind, replan, or refuse at the durability boundary. CommitGuard, a fail-closed boundary monitor, blocks stale durable-effect attempts on protected commit surfaces when runtimes emit witness, dependency, binding, and eligibility signals. The result is a reporting and runtime-design lesson: endpoint success is a utility metric; authorized commit is a security property.

As the 3D printing market continues to grow rapidly, with an estimated value exceeding $30 billion, cybersecurity risks and attacks targeting additive manufacturing systems are also increasing. These attacks aim to sabotage printed components, steal intellectual property, or even physically damage the 3D printer itself. One major cybersecurity threat in this domain is firmware level attacks, which can be introduced through supply chain compromises, malicious firmware updates, or insider threats that deploy modified firmware to manipulate printer behavior. To defend against such threats, we propose a dedicated hardware based security solution,Firewall3D, that acts as a hardware firewall for 3D printers. Firewall3D continuously monitors physical layer signals, including stepper motor currents, end stop switches, nozzle and bed temperatures and cooling fans, to verify that the printer's physical behavior matches the intended G-code execution. Our experimental results demonstrate that Firewall3D can effectively detect a wide range of firmware attacks that could compromise print integrity, damage printer components, or leak intellectual property. Upon detecting abnormal behavior, the system can immediately trigger an alarm and halt the printing process, thereby preventing further damage and risks.

Brain-computer interfaces (BCIs) are a class of diverse hardware modalities, associated software, and connected devices which are widely used in a variety of fields, including neurosurgery, biomedical data analysis, and neuroimaging. Recent years have seen rapid advancements in BCI technology, and neurotechnology more broadly, with the first devices now passing clinical trials, early examples of consumer hardware entering the market, and many variants of consumer and medical hardware with increasingly extensive capabilities being developed rapidly. However, research and development in security for BCIs–known as neurosecurity–lags significantly behind the capabilities of BCIs themselves. In an effort to address as many vulnerabilities as feasible immediately, in this paper we review the current state of the art in neurosecurity, thoroughly survey the breadth and complexity of both firmly established and highly probable security threats to BCI systems, and provide recommendations of existing methods from cybersecurity, hardware security, and machine learning which can immediately be applied to address some of these gaps in neurosecurity.

Large language models (LLMs) have transformed misinformation from a primarily content-centric problem into a broader ecosystem-level security challenge. When misused, LLMs create risks beyond false content generation, enabling attacks on the social contexts, evidence sources, retrieval corpora, and verification workflows that misinformation defense depends on. In this paper, we introduce a role-layer framework to unify these risks and defenses. The role dimension characterizes LLMs as attackers, defenders, and vulnerable components of verification systems, while the layer dimension covers content, social contexts, evidence environments, and verification workflows. Guided by this framework, we organize LLM-enabled attacks, investigate LLM-based detection and verification methods, analyze vulnerabilities in LLM-centric detection paradigms, and discuss existing countermeasures against LLM-enabled attacks. Building on this synthesis, we identify three key open challenges: moving from static detection accuracy to budgeted ecosystem-level risk evaluation, hardening LLM-centered verification pipelines against adversarial manipulation, and deploying auditable human-in-the-loop verification systems for trustworthy real-world misinformation defense.

In-DRAM Rowhammer defenses pin the mitigation threshold at manufacture time, yet the true Rowhammer Threshold (TRHD) varies with runtime temperature. We propose Dynamic Rowhammer Threshold Management, a defense-agnostic runtime layer that re-sources each defense's threshold from the observed temperature once per epoch via a linear-$T$ model with a VRD-motivated guardband $g$, projecting the result onto SALT-C, PRAC, and TRR through each defense's threshold parameter. A decoupled oracle that scales physical TRHD per-DIMM by $\delta \sim \mathrm{N}(1, \sigma)$ breaks model self-consistency. The layer drives PRAC's 72 staleness breaches at 85$^\circ$C to zero; at $\sigma{=}0.10$, sweeping $g$ collapses PRAC breaches from 38.4 ($g{=}1.0$) to 9.6 ($g{=}0.9$). SALT-C drops from 10 nominal-static breaches to 2 (Dynamic) to 0 (bootstrap), at $\leq$5.1% latency. TRR is capacity-limited; the layer acts as a diagnostic.

Cellular core networks (CNs) are critical infrastructure, yet their internal security model has historically relied on physical isolation: interfaces between core components often operate within an assumed trust zone. As CNs transition to cloud-native deployments, this assumption weakens, expanding the attack surface and enabling external adversaries to reach previously internal interfaces. From a root-cause analysis of security flaws reported in GitHub issues for opensource CN implementations, we found a recurring pattern of blind trust among CN components. Components may omit syntactic validation, fail to enforce semantic invariants, or allocate resources without checking availability. Once internal interfaces become reachable, these weaknesses can lead to severe impacts such as denial of service and session hijacking. We call these vulnerabilities implicit trust errors (iTrue). To detect iTrues and understand their security impacts, we designed iFinder, an LLM-driven multi-agent system that summarizes known flaws, distills them into detection patterns, and applies them to discover new iTrues in CN implementations. To suppress hallucinations produced by large language models (LLMs), we built an innovative strategy that crosschecks both 3GPP specifications and CN code to capture existing protection missed by the agents. Further, we developed a technique that uses LLMs to generate proof-of-concept (PoC) exploits for potential iTrues and iteratively refine the PoCs by automatically executing them against CN implementations and analyzing results. Running iFinder on seven prominent open-source CN implementations, we discovered 84 previously unknown vulnerabilities. Among them, 83 have already been confirmed and 81 have been assigned CVEs. Importantly, a session-hijacking flaw has been confirmed on real-world commercial 5G core networks.

Byzantine-robust aggregation rules such as multi-Krum assume a central coordinator, and decentralising them is obstructed by the rules themselves: they are globally coupled, non-associative, and discontinuous, so an ulpscale perturbation can flip the selected subset, moving the output by a non-vanishing amount. None of this prevents coordinator-free replication, because a robust rule needs no agreed order of contributions, only an agreed set and an agreed exclusion predicate, both of which converge without consensus. ACFA (Accountable Consensus-Free Aggregation) replicates a content-addressed OR-Set of signed contributions and a grow-only set of self-authenticating equivocation proofs, offline-verifiable by anyone. Aggregation is a deterministic pure function of the converged product state: fixed-point integer arithmetic over a hash-canonical order, ties broken by content hash. We prove that any pure function of a converged product of CRDTs (non-monotone, non-associative, or stochastic) inherits Strong Eventual Consistency, together with its converse; the contribution is the composition of a data lattice with an evidence lattice applied to a robust selector, not the elementary lifting step. A prototype (10 nodes, 3 Byzantine) passes 16/16 falsification checks: byte-identical roots under adversarial gossip, deterministic re-convergence after late equivocation proofs, partition recovery, and three byte-identity-breaking ablations. The guarantee is consistency, not accuracy; robustness is imported, conditional on 2f + 3 admitted contributions (at most f Byzantine) and a stated quantisation-margin condition.

Vision-Language Models (VLMs) are rapidly deployed on human-facing wearable devices such as smart glasses to enable multimodal perception and AI-assisted decision-making. While prior research has demonstrated the risks of visual prompt injection into digital image inputs of VLMs, the unique security challenges posed by the increasing integration between physical environments and wearable intelligence, such as those embodied in VLM-enabled AI glasses, remain underexplored. Toward understanding and modeling such threats, our work characterizes how malicious textual information embedded in physical environments introduces a high-priority visual channel for indirect prompt injection, where scene texts that hinder or evade human perception could hijack VLM models' behavior. Such Physical Prompt Injection Attacks can not only disrupt normal tasks of VLM-enabled wearable devices, but also steer models to produce profane, biased, or even untruthful outputs. Using physically captured photos from AI glasses in over 200 real-world environments, our analysis identifies 6 representative threat vectors of physically injected prompts, and further evaluates their impacts on 12 VLM models. Results show that these attacks consistently manipulate model outputs across integrity- and safety-critical tasks, achieving attack success rates of up to 96% and 60% in simulated and real-world settings. Our analysis confirms that multiple models exhibit excessive blind trust in environmental text, ignoring the actual visual context and producing completely opposite summaries or directives. We further propose two targeted defense strategies, including a mask-based external filter and a semantic-vector-based internal detector, to effectively reduce the success rate and safety impact of these attacks.