CyberSec Research

As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own. We show this net has a fundamental hole. A distributed backdoor splits a harmful payload across agents, so every local check passes while the assembled object is the attack. The monitor can be right on every step and still miss the attack. The problem is not splitting itself: split fragments can still leak suspicious tokens or provenance edges. The hard case is \emph{local benignness}. No fragment carries the harm, and what is left looks like ordinary benign traffic. We formalize this as an \emph{observability boundary}: a monitor catches only what its view can tell apart from benign traffic. We prove that once the fragments look benign in the monitored view, no detector on that view can catch them, however strong it is. Across a controlled testbed, an external benchmark, and end-to-end agent runs, local monitors lose the signal exactly as local evidence disappears, and it returns only when the monitor sees the assembled object. A monitor trained only on benign traffic recovers the attack's code structure across held-out encodings (0.874 mean AUROC). A decoded-view gate, given the encoding family, blocks every tested attack. But seeing more is not enough: full-trace monitors and decoders still fail unless they reach the representation where the payload is exposed. Local safety is not global safety when harm is compositional, and the open problem is finding that representation.

Following the rapid progress of generative Artificial Intelligence, there is a growing threat posed by conversational scams. These scams often span over multiple weeks or months, gradually build trust and request for money or sensitive information. Existing scam-detection systems mainly focus on isolated messages, which renders them inadequate against this evolving threat. This paper extends single-message phishing detection and presents an explainable agentic system for detecting sophisticated conversational scams. It also introduces ConScamBench-278, an initial public multi-category benchmark for conversational scam detection spanning eight scam types, released to support reproducible evaluation and future expansion. On isolated messages the single-message detector attains 100% phishing recall, while the conversation-level detector identifies all conversational scams in the public LoveFraud02 corpus (83/83) and reaches 97.8% accuracy (95% CI [95.4, 99.0]) on ConScamBench-278. Two user studies (N = 100 and N = 45) further motivate the system: participants report frequently experiencing uncertainty when judging suspicious conversations. In an uncontrolled pre/post comparison, users self-reported trust, self-confidence, and perceived need for AI-based scam detection all increased (p < 0.001, Wilcoxon signed-rank). The system also receives a System Usability Scale score of 74.7 (95% CI [72.5, 76.9]), above the established usability benchmark.

Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools. Existing approaches mainly optimize attack success and preserve artifacts such as benchmarks, payloads, or attack programs, which record where attacks succeed but not the enabling conditions behind unsafe agent behavior. We study automated red-teaming for production LLM agents using one agentic research environment to discover reusable vulnerability knowledge about another. We present AHA, a falsifiable discovery loop that proposes a vulnerability hypothesis, constructs a falsifier, instantiates a valid attack, executes it in a sandboxed harness, reflects on the trajectory, and promotes confirmed findings into a Vulnerability Concept Graph (VCG). Each concept links an attacker-facing surface to an unsafe trajectory through a claim, enabling condition, falsifier, transfer prediction, and supporting evidence. Across Claude Code and Codex on three scenarios covering direct and indirect attacks, the discovered concepts reveal a reusable vulnerability core across models and agents. A frozen VCG requires no further search and outperforms the strongest frozen discovery baseline by 14.2 percentage points under the same single-shot protocol, while transferring across scenarios and attack channels. The resulting VCG provides an auditable artifact for production safety teams to inspect vulnerabilities, validate patches, and accumulate reusable safety knowledge. Our code is available at https://github.com/henrymao2004/Auto-research-red-teaming-in-sleep.

Network-based anomaly detection for IoT devices has matured to the point of reporting strong detection accuracy, yet most published systems stop at raising an alert and leave the question of automated enforcement to future work or to a programmable data plane that few real networks operate. This paper presents an access-control architecture that closes that loop using only standard, already-deployed protocols. Devices authenticate via IEEE 802.1X with EAP-TLS, and a RADIUS server acts as a continuous policy decision point capable of evicting an active session via a Change-of-Authorization Disconnect-Request and permanently excluding a device through certificate revocation. A central, contextual access policy engine continuously consumes the anomaly detector's output and actuates this response over a narrowly restricted channel to the RADIUS server; the same engine is designed to be extensible to other access types, though this paper evaluates only the network access-control mechanism. This mechanism is driven by an anomaly signal from a one-class detector adapted from a prior MUD/SDN-based design, replacing its per-flow multi-model pipeline with passive traffic capture and a single fused model that combines a cluster-based, a volumetric, and a protocol-signature score. On a single testbed device, the detector reaches an AUC of 0.9964 and detects all 24 evaluated attack scenarios (eight attack types at three intensities) using roughly 43$\times$ less training data than the reference design, and the resulting alerts reliably trigger the automated disconnect-then-revoke response, which we measure to evict a device from the network in 335.8\,ms on average and complete certificate revocation in a further 111.5\,ms. We report this evaluation as a demonstration of the closed-loop architecture rather than of the detector itself, and discuss multi-device generalization as a concrete next step.

Blockchain governance, the set of processes by which decentralized protocols evolve, remains a fundamental challenge in balancing adaptability, security, and stakeholder representation. This technical report analyzes Cardano's Voltaire governance system, the on-chain framework introduced via CIP-1694 and enacted through the Chang hard fork in September 2024, and lays down a corresponding research program. We make two contributions. First, we provide a complete technical specification of Voltaire's mechanisms, including its three-body architecture, seven governance action types, voting rules, and its constitutional framework; this specification is sufficient for implementation or formal analysis. Second, we establish a research agenda for principled governance optimization, including design of an agent-based simulation platform, analysis of delegation dynamics, optimization of multi-objective parameters, and game-theoretic incentive design; we provide preliminary results, including a formal governance kernel: a minimal executable model capturing self-amending governance as a state-transition system and enabling rigorous safety and liveness analysis. Our report offers a comprehensive technical overview and invites the research community to advance blockchain governance science through rigorous study of Voltaire as a live, large-scale experiment now managing a treasury valued at approximately \$235 million (1.47B ADA as of early July 2026).

Opal2 self-encrypting drives provide hardware-based disk encryption serving as an additional layer of protection, or a replacement, for software-based solutions. This paper presents a case study of real-world Linux integration of Opal2 drives and the security of Opal2 firmware. The study was conducted on a testbed of 38 commercial off-the-shelf Opal2 drives from various vendors using a black-box approach. We identified several firmware security issues and incompatibilities, which we responsibly disclosed to respective vendors. Our findings led to improvements in Linux disk encryption tools used across all major Linux distributions. To enable independent evaluation for the public, we release our test scenarios for Opal2 drives as an open-source toolset.

Adversary emulation plans describe multi-step attacker procedures using MITRE ATT&CK techniques, privilege requirements, and observable telemetry. Translating them across operating systems supports cross-platform defender evaluation, and large language models (LLMs) can automate this task. However, a translation may only rename tools while retaining source-platform logic, giving defenders little target-platform coverage. Binary scoring can overestimate fidelity because it measures countable features rather than structural, observable, and rule-level equivalence. Graph-Based Structural Evaluation (GBSE) models each procedure as a directed attributed graph and calculates normalized Graph Edit Distance (GED) across four layers: technique, tactic, telemetry class, and Sigma logsource. GBSE was applied to a 29-step ALPHV/BlackCat Windows-to-Linux plan, comparing a reconstructed Windows control with the unmodified LLM-generated Linux version. Technique and tactic structure were fully preserved (GED=0, similarity=1.000). Telemetry similarity fell to 0.897 (GED=3) because three steps contained unmapped or drifting observables, while Sigma logsource similarity was 1.000. Every state was classified as Medium Fidelity, with a best composite score of 0.674. The 0.80 deployment threshold was not reached because technical realism scored 0.43 against the required 0.990. The framework includes bipartite GED, a telemetry-intent parser that converts free text into observable classes, and 49 validated Sigma rules: 19 for Linux and 30 for Windows. The rules provide complete ATT&CK technique coverage and pass validation with zero findings. Additional analysis reveals technique-level divergence, including RDP-based external access mapped to unencrypted exfiltration and credential-store access mapped to remote-system discovery. Results were reproduced and verified against recorded outputs.

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 $μ$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 4,685 source-to-sink data-flow analysis tasks from 50 open-source Android apps. Compared with standard OpenCode, FlowArk-enabled OpenCode maintains comparable analysis quality while reducing end-to-end API cost by 26.83%. In addition, under a USD 100 budget, FlowArk completes 36.66% more tasks (1,060 vs. 776).

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.

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.