Papers

Safety alignment in large language models (LLMs) remains brittle against a growing spectrum of attacks. Jailbreak attacks bypass safety mechanisms through crafted prompts, while neuron-level attacks directly prune safety-critical neurons post-deployment. Both exploit a common weakness: safety-relevant information concentrates in a sparse neuron subset. We present NeuronGuard, a fine-tuning-stage defense that simultaneously hardens LLMs against both attack classes by redistributing safety signals across a broader set of neurons. NeuronGuard dynamically identifies safety-critical neurons via periodically refreshed per-layer linear classifiers, forces refusal behavior under deliberate neuron ablation, and applies KL-divergence regularization for distributional consistency. A randomized gradient projection strategy preserves downstream task utility by resolving conflicts between the defense and task objectives. We provide a formal guarantee that NeuronGuard strictly reduces the attack success rate (ASR) upper bound, and experiments across three LLMs, six state-of-the-art attack strategies, and multimodal settings confirm near-zero ASR while maintaining task accuracy, including against white-box adaptive adversaries.

Federated video anomaly detection trains model collaboratively without sharing raw surveillance footage, but limited server-side visibility lets compromised clients to inject backdoor via malicious updates. This paper introduces STAIN-FL, a stealthy targeted backdoor attack injection framework that uses naturally occurring surveillance conditions, including low-light scenes, indoor settings, and crowd density, as contextual triggers. STAIN-FL combines anomaly-to-benign label manipulation with gradient masking over least-updated coordinates to preserve clean accuracy while inducing trigger-conditioned misclassification. We evaluate STAIN-FL on UCF-Crime using 1024-dimensional I3D features in a non-IID four-client multi-agency setting, comparing FedAvg and FedProx under sparse and continuous attacks. Results show that sparse attacks have low-detectability, operationally significant attacks rather than high-intensity attacks: they keep the mean clean-accuracy drop below $2\%$, yet still misclassify more than half of triggered anomalies at peak backdoor accuracy under FedAvg ($56.7\%$) and FedProx ($54.2\%$). Under FedAvg, the sparse backdoor remains above the $25\%$ backdoor-accuracy threshold for an average of $336$ post-attack rounds, highlighting the persistence risk of contextually triggered attacks in surveillance systems.

This work presents a comprehensive analysis of contemporary hardware fuzzing techniques applied across three major abstraction layers: Instruction Set Architecture (ISA), microarchitecture, and Register-Transfer Level (RTL). Our study examines key factors including input stimulus quality, mutation strategies, feedback mechanisms, target platforms, reference models, and achieved coverage. We find challenges, goals, and design trade-offs vary significantly across abstraction layers. We further identify several unmet needs in current hardware fuzzing practices, such as intelligent input generation, reliable and scalable golden reference models, expressive feedback channels, and cross-layer integration. Building on these insights, we outline future research directions, including hybrid fuzzing frameworks, AI-assisted test generation, scalable reference models, standardized evaluation metrics and benchmarks, and human-in-the-loop automation for guided exploration and analysis. Together, they aim to unlock efficient, reliable, and comprehensive hardware verification solutions.

Open, cloud-native, and AI-enabled 6G architectures make network functions easier to deploy, observe, and replace, often implemented with separate software modules. However, each explicit interface can also create an entry point, trust transition, and lateral-movement route from a cybersecurity perspective. This paper formulates architectural disaggregation as a graph-based Stackelberg design game for 6G system security. A deployment graph specifies candidate 6G system seams, while an architecture-dependent directed attack graph specifies externally reachable functions and multistage paths. The defender commits to seams and allocates hardening and monitoring; an informed attacker then chooses a path and effort. Because edge traversal and evasion factors compose multiplicatively, the attacker's path response becomes a shortest-path problem after a logarithmic transformation. Convex effort costs admit a conjugate representation, and, for each fixed architecture, the defender's control problem is a convex exponential-epigraph program solvable by path generation. We derive an architecture-comparison criterion, a threshold for AI transducers within 6G systems that jointly add visibility and exposure, and comparative statics for attacker entry and bypass innovation. Experiments with stylized standards-anchored O-RAN/6G systems over RAN, RIC, core, cloud, and edge-AI functions show that neither full integration nor maximal disaggregation is generally best. Uncontrolled seams can increase risk, whereas selectively monitored and hardened seams can improve the Stackelberg objective. We find a boundary is worthwhile only when its detection and containment gains exceed its added attack opportunities and coordination cost.

Everything a language model sees is tokens. The serving stack knows what each span is – user input, tool output, instructions – but the model must keep track of that itself, and can lose track or be confused: text can be written to read like anything. Prompt injection is a natural exploit of this phenomenon. By scrambling the model's understanding of span identity, an attacker can induce unwanted and dangerous actions. Adding a non-textual channel to the model's input – a way to communicate span identity beyond text – mitigates this class of attack. We thus introduce a general steering technique called Semantic Overlays: small learned adapters applied at chosen prefill positions to a frozen model's residual stream. Laying an overlay over a span creates an out-of-band annotation channel that cannot be replicated by tokens. Unlike steering vectors, Semantic Overlays are trained, adaptable, and selectively applied. An overlay can encode complex semantics that reshape how the model perceives the marked span: asked to copy a code snippet under an overlay asserting a different programming language, the model rewrites the snippet in the asserted language. Overlays compose, allow transparent reading of underlying content, and can carry complex payloads – including imperatives the model will follow. An overlay which marks a span as "non-executable" defends against the broad class of prompt injections that add instructions in untrusted context. We report strong results on five prompt injection benchmarks: SEP separation rises from 24.3% to 99.0% with utility unchanged (our scoring rule; we correct a defect in the published grader), TensorTrust attack success falls from 34.8% to 6.2%, AlpacaFarm from 99.0% to 0%, and the overlay beats every published PIArena defense that leaves the model able to answer – while marked spans stay readable, all at >95% character similarity to the original.

The Agent Payments Protocol (AP2), introduced by Google, enables large language model (LLM)-driven shopping agents to authorize and execute payments on behalf of users. Its signed Checkout and Payment Mandates protect the integrity of transaction data after signing. Agent interactions and external inputs that shape a transaction before authorization remain outside that protection, including Agent-to-Agent Protocol (A2A) messages and Model Context Protocol (MCP) tool calls. Prior work identified replay and prompt-injection attacks in AP2 v0.1. AP2 v0.2 addresses some of these issues but adds capabilities and deployment assumptions that require renewed analysis. We present a systematic security analysis of AP2 v0.2 based on its roles, transaction lifecycle, deployment architectures, and trust boundaries. We divide the lifecycle into five phases and identify five deployment architectures. Using MAESTRO (Multi-Agent Environment, Security, Threat, Risk, Outcome), we model four threat actors, eleven attack surfaces, eighteen adversary capabilities, and six attacker goals. The resulting catalog contains 48 threats spanning five attack families. We score these threats with the Artificial Intelligence Vulnerability Scoring System (AIVSS), identifying eight that reach the High band in at least one architecture. Because no complete public AP2 deployment was available, we build a testbed spanning all five architectures and develop five proof-of-concept demonstrations covering all eight High-risk threats and their mitigations. We also develop a deployment-aware scanner that maps applicable threats to static, cross-role consistency, and adversarial checks. Our analysis shows that valid mandate signatures alone do not ensure that an agent-mediated transaction reflects the user's intent when its pre-authorization context is manipulated.

This paper evaluates quantum and AI-accelerated risks to TLS 1.3 cryptographic dependencies under an evidence-tiered model, distinguishing mechanism-backed threats (Shor algorithm against RSA and ECC) from contingency-backed risks to lattice-based post-quantum cryptography (PQC) and hypothesis-only risks to hash-based and symmetric primitives. We do not identify any known breaks of ML-KEM, ML-DSA, SLH-DSA, or AES-256. Instead, we use explicit scenario assumptions, organized as a four-scenario capability model with parameters and pseudocode for reproducibility, to stress-test migration timelines accompanied by parameter sensitivity analysis and explicit falsification analysis. The primary methodological contribution is a reproducible scenario-estimation instrument together with its explicit update mechanics: every parameter is a named, anchored quantity that can be varied and the model rerun; a stated protocol maps observed conformance to, or deviation from, the modeled curves onto revisions of specific parameters, so progressive refinements can be tested against accumulating historical data. The paper is a methodological companion to quantum resource-estimation studies and to expert-elicitation timeline surveys such as the Global Risk Institute quantum threat reports, with its revision rules stated explicitly. As of mid-2026, the model does not show any NIST-approved algorithms as broken. Instead, the vulnerability spectrum under different scenarios shows RSA risk crossing the 50% threshold between 2030-2032 and the PQC risk becoming a non-zero risk after 2032-2035 under contingency scenarios conditional on the unproven dimension-collapse. We urge PQC migration as mandatory per the 2030 and 2031 federal deadlines and by Mosca HNDL reasoning, and that crypto-agility and hybrid cryptographic deployment be considered necessary complements to any PQC migration efforts.

Existing Rowhammer-based inference-time backdoor attacks design their bit-flip strategies purely at the algorithmic level, without accounting for the bit-flips that the underlying DRAM hardware will actually produce. This disconnection between the algorithmic backdoor construction and its hardware realization leads to unreliable attack performance, as collateral bit-flips at unintended locations degrade both the attack success rate (ASR) on triggered inputs and the test accuracy (TA) for normal inputs. Consequently, the performance of such attacks varies significantly across different DRAM devices, as each device presents a unique set of exploitable bit-flip locations. This work presents ROBBIN, a hardware-aware Rowhammer-based backdoor injection attack that integrates the device-specific vulnerability into the backdoor construction process. ROBBIN first characterizes the bit-flip patterns of a target DRAM and uses this information to iteratively select DRAM page mappings for the model weights that would maximize ASR while preserving TA under Rowhammering. By treating every hammering-induced bit-flip as an integral part of the attack design rather than first constructing a hardware-agnostic backdoor and dismissing collateral flips as side effects, ROBBIN produces backdoors that remain robust across devices. Evaluated on ResNet-20 and VGG-16 with CIFAR-10 across three commodity DDR4 chips, ROBBIN consistently achieves close to 90% ASR while maintaining TA above 83%, demonstrating reliable backdoor efficacy across diverse DRAM devices.

The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness introduces a severe server-side threat we term TrustShift: a compromised MCP server behaves benignly during an initial conditioning phase, building operational reliance and suppressing agent skepticism, before switching to an adversarial payload once an interaction threshold is reached. The evasion is temporal, not syntactic: benign at deploy time, the server's defection is invisible to predeployment static analysis, which sees only the honest phase. Switched payloads range from overt structural violations to schema-valid manipulations, the latter preserving outer protocol compliance to evade runtime middleware filters. Crucially, TrustShift originates in the server-controlled tool channel, not user prompts (unlike indirect prompt injection) or the transport (unlike man-in-the-middle): the adversary is the trusted server endpoint itself. We introduce TrustShiftProbe, an evaluation and defense framework with four contributions: (1) a stateful temporal threat model of the agent-server lifecycle as a benign conditioning phase followed by an adversarial defection at a trust horizon; (2) a language-agnostic attack engine that instantiates each variant as a compromised MCP server across four production domains; (3) SHIELD, a multi-tier, zero-oracle runtime defense at the MCP transport boundary that audits server payloads against behavioral baselines learned during clean trust windows; and (4) a taxonomy of nine TrustShift variants spanning three execution mechanisms (structural violation, semantic corruption, scope expansion) and three adversarial objectives (disruption, exfiltration, and their combination). Across frontier proprietary and open-weight models, TrustShift attacks achieve a 69.5% mean attack success rate that SHIELD mitigates to 42.7%.

Perimeter-based security appliances, such as firewalls or Intrusion Detection Systems, are ineffective against modern attacks that use pivoting, wherein attackers "pivot" traffic through compromised hosts to gain access to additional targets that would otherwise be inaccessible. Due to the legitimate appearance of the relayed traffic, pivoting is extremely difficult to detect. Although the consequences of these attacks are known to be severe, existing defenses suffer from drawbacks such as high processing delays, low accuracy, or reliance on network-wide participation, making them inconvenient or even ineffective. This work presents Stitch, a host-based system that uses the programmable kernel to detect pivoting in real time. By observing host-traversing flows, Stitch uses process tracing to effectively combine system and network-level information, connecting incoming and outgoing communications and identifying pivoting characteristics between them. Showing 31% gains in accuracy over state-of-the-art pivoting defenses and a maximum false positive rate of 0.006% over two separate real-world deployments, Stitch covers the gap in current pivot detection solutions by providing accurate, lightweight, and independent coverage for vulnerable hosts in a network.

In CLAUDE.md, "do not" is a natural-language instruction that the model interprets. Claude Code's deny is a built-in control that blocks an action before the agent can take it. Both can express the same security goal, but they control the agent in different ways. We measure this gap in 481 public CLAUDE.md files. An LLM matched the extracted candidate rules against Claude Code's documented controls, and two security practitioners independently checked a sample without seeing the model's answers or each other's labels. Depending on how closely a control had to match the written rule, only about 4-16% of the retrieved security rules had a matching built-in control. Under the strictest standard the estimate was 4.4% (95% CI: 2.6-6.7%), and the two annotators agreed closely on which rules had a match. A manual review of complete files found that our extraction method captured 66.3% of eligible security rules; the reported rates therefore apply to the rules it captured. This is a usable security problem: CLAUDE.md is a write-only channel. A developer writes a security rule but gets no feedback on whether a control will enforce it. The same plain-text form hides two kinds of rule: those a permission rule, mode, or sandbox can enforce, and those left to the model to interpret.

Machine-learning-based anomaly detection is increasingly used in industrial control systems (ICS), yet most studies assume that detector training data is trustworthy. In practice, training data may be corrupted through compromised logs, labeling errors, manipulated historian records, or unsafe retraining processes. This paper evaluates the robustness of offline ICS anomaly-detection pipelines on the Secure Water Treatment (SWaT) benchmark under training-time contamination. We assess 11 heterogeneous anomaly detectors under three contamination strategies: random injection, similarity-targeted injection, and feature-noise injection. The first two insert attack samples into the nominal training pool, while the third adds bounded Gaussian noise to selected normal training samples. These attacks are contamination-based rather than gradient-driven poisoning methods. Contamination budgets from 1% to 10% are evaluated using clean validation and test sets under a unified offline protocol. The results show that robustness is strongly model-dependent and cannot be predicted from clean-data performance alone. Injection-based contamination causes the greatest degradation, particularly for local-density and distance-based detectors, whereas feature-noise contamination has a comparatively limited effect. PCA, SVM, HBOS, and IForest remain relatively stable, while the tuned neural detectors demonstrate intermediate robustness. Overall, the findings highlight the importance of training-data integrity in ML-enabled ICS monitoring, subject to the evaluated dataset, models, and threat assumptions.

The continual evolution of malware variants necessitates detection systems that can adapt to new threats without retraining from scratch. However, continually updating models on new data often leads to catastrophic forgetting, where previously learned knowledge is overwritten. While continual learning has been increasingly explored for malware detection, the specific setting of Few-Shot Class-Incremental Learning (FSCIL), where new malware classes must be learned from only a small number of labeled examples, remains comparatively underexplored. Therefore, this work investigates the FSCIL setting for malware classification. To address the stability-plasticity dilemma, we propose a hybrid framework that leverages a Self-Supervised Learning (SSL) backbone initialized through domain-specific pre-training on malware packets. Our method incorporates Low-Rank Adaptation (LoRA) to efficiently adapt the model during the base session while freezing the core backbone to preserve previously learned representations, alongside a prototype-based classification head for incremental sessions to establish robust decision boundaries from limited samples. Extensive experiments across several datasets demonstrate that our approach consistently outperforms prior malware FSCIL baselines and achieves state-of-the-art performance.

Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities into agents? Thus we propose InjecMEM, a novel memory injection attack paradigm that requires only a single interaction (no read/edit access to memory store) to steer later responses of related queries toward a pre-specified output. Guided by the retrieval-then-generate mechanism of memory systems, we craft the injection with a retriever-agnostic anchor and an adversarial command. The anchor contains high-recall topical cues so that downstream retrieval consistently associates the record with the target topic. The command is a short sequence optimized to remain effective under uncertain fused contexts, variable placements, and long prompts so that it reliably steers outputs once retrieved. We learn the command via gradient-based coordinate search, averaging over synthetic prompt templates and insertion positions, and extend it to joint optimization across backbones to study transfer. Evaluated across multiple memory systems and backbone models, InjecMEM achieves reliable topic-conditioned retrieval and targeted generation, remains effective under memory drift, and leaves non-target queries unaffected. Our results underscore the need to harden memory systems and provide a reproducible framework for studying agent memory.

Anomaly detection is often applied to data stored in relational databases, yet most existing methods require flattening multiple tables into a single feature matrix. This flattening can obscure entity identity, schema structure, and multi-hop dependencies, limiting the detection of anomalies that depend on relational context rather than isolated feature values. Beyond preserving relational structure, relational anomaly detection raises an additional challenge: how to incorporate symbolic behavioral evidence into learned relational representations. To address these challenges, we study relational anomaly detection, where the goal is to identify anomalous entities or events in a multi-table database. We propose RAD, a rule-augmented relational anomaly detector that combines heterogeneous graph representation learning with refined symbolic rule signals. RAD derives candidate rules from random-forest paths over flattened summaries of the entities or events being scored, refines them into compact interpretable predicates, injects the resulting rule features into the graph model, and learns anomaly scores using reconstruction-based and pairwise-ranking supervision. To evaluate this setting, we introduce a relational anomaly detection benchmark spanning three settings: LANL cybersecurity event detection and two unexpected user-churn anomaly tasks derived from Amazon and H&M relational databases. Experiments show that RAD improves anomaly ranking over flattened tabular detectors and relational baselines under natural class imbalance, achieving the best average rank on AUROC and AUPRC across the benchmark. Ablations show that direct rule injection and ranking-based supervision are key contributors to performance, while edge reconstruction is not uniformly beneficial. Our code and data are available at: https://github.com/noahd15/RAD_RelationalAnomalyDetection.

Homomorphic-encryption blockchain frameworks for IoT sensor aggregation generally rely on classical cryptographic hardness assumptions and seldom account for network topology in liveness and performance analysis. This work introduces Phi-PHE-BC, a topology-aware homomorphic blockchain architecture for secure and privacy-preserving IoT sensor data aggregation. The framework combines threshold Paillier decryption with graph-parameterized security and performance analysis, linking protocol behavior to the validator graph. On-chain Paillier ciphertexts support homomorphic aggregation while providing IND-CPA confidentiality under the Decisional Composite Residuosity assumption, and authentication signatures provide EUF-CMA transaction integrity. Threshold partial-decryption shares are protected by a noise-flooding wrapper that provides information-theoretic privacy under the configured statistical-hiding condition. Under partial synchrony and Byzantine fault-tolerance assumptions, liveness requires validator connectivity kappa(Gv) >= f+1. We derive topology-dependent throughput bounds for tree, star, mesh, and scale-free networks, together with a per-block communication-cost model. A game-theoretic analysis shows that honest validator participation is a dominant strategy under the stated utility model, yielding an all-honest Nash equilibrium. Experiments on Hyperledger Fabric 2.5 show lower end-to-end latency than the selected traditional PHE-blockchain baseline while maintaining controllable threshold-decryption overhead. Results across topology scaling, validator sensitivity, threshold decryption, and Byzantine-load experiments indicate that Phi-PHE-BC is a practical architecture for secure, privacy-preserving, and topology-aware IoT sensor aggregation.

Instance encoding is a popular empirical technique for privacy enhancement when sharing data to an untrusted server. It transforms sensitive data through an encoding process before sharing, with the hope that the encoding process retains utility but makes it hard to reconstruct the original data. However, most work offers no theoretical guarantee that the encoding process is actually irreversible. A recent work derived a mean-squared error (MSE) bound limiting any adversary's reconstruction accuracy, offering one of the first theoretical results in this domain. This bound, however, has three critical limitations: it is often too loose, only works with randomized encoders (excluding many deterministic encoders practitioners use), and only bounds MSE. We introduce a family of new bounds that (1) are tighter, (2) applicable even to fully deterministic encoders, and (3) can extend beyond MSE to other norm-based similarity metrics, by properly accounting for the encoder's spectral structure. We evaluate our bounds across a range of encoders, datasets, and attacks, showing they hold consistently and improve upon the existing bound.

Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU nondeterminism, reporting a >200x slowdown for a steganographic adversary under benign prompt traffic. This bound assumes a passive attacker; we show it degrades sharply against an adversary who instead controls the prompt distribution. Because the verifier's admissible-token-set size is driven by the model's own output entropy, prompts engineered to break grammatical and sub-word structure – rather than benign conversational traffic – widen that set and open a materially larger covert channel. Across six instruction-tuned models spanning 1B to 32B parameters and three random seeds, our strongest attack (character- and script-level disruption) roughly doubles bits leaked per token relative to benign prompts, cutting the slowdown factor to 60x - 118x. These results indicate that static, benign-traffic-calibrated thresholds are insufficient for this defense, and that jitter-forgiveness thresholds should instead be calibrated dynamically against local token entropy.

Solid-state drives (SSDs) are built on NAND flash memory and expose it to the operating system through a block-based storage interface. As NAND flash has special read/write constraints due to its hardware nature, a translation between OS-level I/Os and raw flash memory I/Os is needed. This results in a flash translation layer (FTL) that creates a “trusted computing base” due to its physical isolation from the OS. Building on this trusted computing base, some security designs (e.g., data recovery from malware attacks) can ensure strong data security properties even if the OS is compromised. However, they mostly require modifying the FTL's firmware code, which is hard in practice because the traditional block-based FTL does not provide an interface to modify its internal functions. New flash storage interface designs, such as open-channel SSDs or zoned namespaces, have moved key FTL functions into the OS. These interfaces ease modification of FTL functions, at the cost of blurring the trusted boundary, as the FTL is no longer isolated from the OS. In this work, we have introduced SxSSD, a secure yet extensible software-defined SSD design. By decoupling internal policy definitions from primitive FTL mechanisms, we allow trusted applications to dynamically and securely define FTL policies and the exposed storage interface (achieving increased flexibility compared to open-channel and zoned namespaces SSDs). Most significantly, SxSSD retains the isolation of traditional FTL execution (achieving security similar to traditional block-based SSDs). We have identified and addressed key security challenges introduced under a compromised OS. In addition, we have implemented a prototype of SxSSD and evaluated its overhead with different FTL policies and storage interfaces. Experimental evaluation demonstrates that the overhead incurred by SxSSD is small compared to native FTL implementations.

The massive adoption of Internet of Things (IoT) devices across critical domains such as healthcare, smart cities, industrial automation, and critical infrastructure introduces significant cybersecurity and regulatory challenges. Current and forthcoming European regulations, including the Cyber Resilience Act (CRA) and the NIS2 Directive, require manufacturers, operators, and other organizations to ensure secure-by-design devices, continuous vulnerability management, and resilient operation throughout the device lifecycle. Traditional certification mechanisms remain static, manual, and difficult to scale across heterogeneous IoT ecosystems. This paper presents CERTIoT-6G, a Security-as-a-Service (SECaaS) framework that enables automated cybersecurity certification and continuous compliance monitoring of IoT devices operating in 5G and future 6G networks. The framework integrates automated compliance analysis, real-time traffic monitoring, and adversarial testing capabilities. We validate the CERTIoT-6G framework on different IoT device categories operating in an advanced 5G testbed. Evaluation results reveal critical compliance gaps, particularly in traffic encryption and availability under unstable conditions, and demonstrate that the framework produces actionable verdicts mapped to regulatory requirements across heterogeneous device types. Furthermore, we show that the monitoring pipeline has a negligible impact on live 5G traffic.

An LLM asked for a trading strategy returns three artifacts at once: a natural-language rationale, an executable implementation, and once run, a track record. Whether these are the same object is rarely checked. We present FIDES, a measurement protocol that treats them as three views to be reconciled rather than one deliverable to be graded. Through dual delivery, a single model call returns both a natural-language strategy with an explicit claimed edge and a self-contained strategy(df) function. FIDES executes the code in a sandbox against a lag-one out-of-sample backtest and scores three concordance gaps: say to do, do to real, and say to result. On 8 liquid US ETFs across four models plus a two-stage elicitation arm, 40 strategies, 2023 to 2024 out-of-sample, three findings stand out. First, concordance does not predict profit: only 2 of 40 strategies beat buy-and-hold, and a plain sma(50,200) rule outperforms every model's mean Sharpe. Second, self-assessment is badly calibrated: 32 of 40 strategies claim to beat buy-and-hold and exactly one does. Third, swapping the language-code judge for a second model flips say to do on more than half of items. Injecting Close.shift(-1) drops do to real by 0.33 on average, while our runtime future-information probe fired on neither clean nor injected code. We frame FIDES as a protocol for measurement fidelity, not a claim about market performance.

Phishing websites are short-lived and rapidly changing, yet many phishing datasets reduce observations to URLs or precomputed features, constraining researchers to predefined representations and discarding the underlying evidence needed to derive alternative features, apply new extraction methods, examine cross-layer relationships, and reanalyze observations as phishing techniques evolve. This study addresses this limitation with a multi-layer active-web dataset comprising 67,502 scans, including 33,387 phishing observations from operational feeds and 34,115 screened benign reference observations. The corpus preserves raw evidence across HTML content and screenshots, URL and redirect behavior, HTTP and security headers, compliance files, TLS certificates, DNS and domain registration, open ports, geolocation and accessibility measurements, and network infrastructure, while explicitly recording unavailable evidence rather than treating it as negative observations. To avoid misleading infrastructure attribution on shared platforms, the study applies a hosting-aware evidence model that masks provider-owned infrastructure signals for free-hosted tenant pages while retaining meaningful page- and transport-level evidence. Characterization reveals systematic differences between phishing and benign websites across web-resource usage, domain maturity, mail and policy configuration, security headers, and infrastructure context. By preserving raw artifacts together with acquisition metadata and explicit evidence availability, the corpus provides an inspectable and reproducible foundation for future phishing measurement and dataset research.

Cyber threat intelligence from underground forums has traditionally relied on passive monitoring. However, as users have become more aware of large-scale data collection, valuable intelligence has become increasingly rare in open forums, often migrating instead to private or harder-to-reach spaces, making passive approaches inadequate. Building on the intuition that relevant information can be obtained through active elicitation, this paper presents DarkBot, to the best of our knowledge, the first multi-agent LLM-based system for active CTI elicitation in underground forums. DarkBot decomposes the interaction task across eleven specialized agents organized into three functional blocks: engagement gating for relevance and safety filtering, context-aware question generation driven by MITRE ATT&CK tactics, and linguistic style adaptation to better align with real forum users. In a controlled evaluation across 100 CrimeBB conversations, the system recovered 72.8% of the validated MITRE ATT&CK techniques present in the original discussions by observing only the initial post at the start of each interaction, and it consistently outperformed a monolithic baseline. The proposed layered safety design contained all injected jailbreak attempts at the pipeline level. These results were further supported by real-world experiments: in a prospective matched deployment, threads assigned to DarkBot accumulated an average of 3.85 more CTI entities than their controls over seven days, and across 104 live forum conversations, the system elicited CTI-relevant disclosures without observed account suspensions, moderator interventions, or explicit accusations of automated participation.

As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention, with closed-source LLMs (e.g., Mythos) delivering advanced cybersecurity capabilities. However, existing open-source efforts remain limited: frontier open-weight models do not provide reproducible cybersecurity training solutions, open-source training solutions focus on isolated tasks and lack scalable agentic data, and scaling agentic rollouts requires strong domain priors. In this work, we introduce CyberFactory, a unified open-source framework that connects data construction, trajectory synthesis, and model training across proof-of-concept (PoC) generation, vulnerability patching, and cybersecurity question answering (CyberQA). CyberFactory transforms public vulnerability artifacts, including CVEs from the wild, into executable and verifiable task instances. It further uses a reusable vulnerability-analysis skill to guide the teacher through source inspection, problem solving with domain prior, and evidence-based validation. The resulting supervision is agentic: the model interacts with tools and target environments and revises its solutions according to execution feedback. Using these trajectories, we train and release \modelname\footnote{Aegis is, in Greek mythology, the protective shield of Zeus and Athena; the name reflects the model's defensive, security-oriented purpose.}, which internalizes the skill-guided procedure without requiring the skill at inference time. On CyberGym, \modelname reaches 52.4% Pass@1 under a one-hour budget, improving over its Qwen~3.5 base model by +22.8 points and outperforming the evaluated general-purpose backbones under the same scaffold.

SIMON and SIMECK belong to a family of Lightweight Cryptographic Algorithms (LCAs) based on the Feistel block cipher, designed for Internet of Things (IoT) devices. As with all Feistel ciphers, they are susceptible to differential cryptanalysis, necessitating rigorous resilience evaluations. While state-of-the-art techniques leverage heuristics and sampling to improve efficiency, little work has applied Machine Learning (ML) guided Graph Representation Learning (GRL) to efficiently identify and visualise high-probability differential clusters. We address this gap by introducing an efficient feature engineering strategy that extracts four differential attributes from a partial Difference Distribution Table (pDDT), revealing structural information concealed in raw differential data. Utilising the enriched features, we construct and compare three ML-guided directed graphs for SIMON$32$ and SIMECK$32$ using K-Nearest Neighbour (KNN), Decision Trees (DT), and Random Forests (RF). To the best of our knowledge, our framework produces the first graph-based visualisation of the differential clustering effect, in which high-probability single-bit differentials form geometrically close clusters in the learned embedding. All three models achieve a precision of $1.0$ in identifying high-probability differentials, confirming zero false positives. KNN achieves the strongest cluster separation, the highest F1 score and the lowest graph construction time of approximately $2.3$ seconds, while DT and RF produce optimal paths with near-perfect regression. The results are consistent across both LCAs, demonstrating the applicability of the framework to other AND-rotation LCA families.

Shielded UTXO-based protocols are becoming a core form of privacy infrastructure for DeFi. Unlike mixers that organize privacy mainly around deposits and withdrawals, these protocols allow assets, once inside the shielded pool, to continue moving and being re-spent within the hidden state, and to become public only when users withdraw or interact with public DeFi protocols. Their anonymity is therefore no longer a flat pool-size problem, but a provenance problem that propagates across the note/UTXO, proof, and transaction layers. Yet, a unified analysis framework for this setting is still missing. We propose a layered system model and an analysis pipeline that uses prior history as the temporal baseline, applies cumulative pruning and cross-proof propagation to each proof's Commitment Set, and recursively traces the survivors through historical hidden-state transitions to derive the final transaction-level Anonymity Set Size. We evaluate our methodology on the complete on-chain histories of all four Railgun production deployments and five independent Hinkal pools across six EVM chains, analyzing 186,356 unshielding spend transactions. Using only public protocol traces and constraints, our non-heuristic analysis yields mean Anonymity Set Size reductions of 40.1%-59.0% relative to each deployment's temporal baseline; 3,679 transactions retain at most 10 addresses, including 1,228 singletons. Public token constraints are the strongest and most stable source of pruning in both protocols, while the effects of tree number, proof roots, and value constraints vary with protocol design and historical state. Together with representative cases, these results reveal interpretable anonymity-loss patterns and implications for user behavior and future protocol design.

Symbolic protocol verification models the network attacker as a Dolev–Yao (DY) intruder, which does everything its knowledge permits, whether or not it serves any purpose; real adversaries instead maximise utility, attacking only when the payoff is positive. We introduce a rational Dolev–Yao attacker, a DY intruder whose actions carry costs and whose security-violating goals carry rewards, and call a protocol rationally secure when no intruder strategy achieves a violation with strictly positive utility, expressed in a weighted fragment of ATL (WATL). We prove this decidable for a bounded rational DY intruder over a finite cost-annotated concurrent game structure, characterise its complexity, and show it strictly refines DY security: some protocols are DY-insecure yet rationally secure, separated by a computable threshold. We illustrate the framework on two contrasting use-cases: an authenticated payment under session uncertainty, where a rational intruder must strategise across indistinguishable sessions and its imperfect information strictly raises the attack cost a designer must price against; and ThreeBallot, a cryptography-free scheme where we pinpoint the bribe-to-benefit ratio below which no rational coercer attacks.

Conventional network threat detection primarily relies on packet-level, flow-level, or host-level telemetry. This paper investigates a different observation surface: unintended electromagnetic(EM) emissions generated by network interface card(NIC) activity, and asks whether such physical leakage contains sufficiently structured information for network threat-behavior recognition. We present NICWhisper, which externally captures NIC EM emissions, transforms raw measurements into time-frequency representations, and recognizes network behaviors without inspecting packet contents or host-side runtime states. Rather than competing with traffic-based detection, NICWhisper exploits the physical manifestation of traffic-driven NIC activity, whose timing, rate, concurrency, and burst organization naturally shape the measured EM leakage. We construct a NIC EM dataset covering active benign workloads and seven representative threat behaviors under diverse execution conditions, and systematically evaluate signal dependence, execution variation, measurement perturbation, and cross-device transfer. NICWhisper achieves 80.67% Macro-F1 across eight behavior classes, while further experiments show that the observed behavior-related information extends beyond simple signal magnitude and remains partially transferable across execution conditions and NIC hardware. These results establish NIC EM leakage as a complementary physical observation source for network security monitoring when direct access to conventional traffic or host telemetry is limited or undesirable.

Agent runtimes can Checkpoint an execution, Fork it, Restore a checkpoint, or Merge branches without restarting a task. We call these operations execution edits, with Checkpoint recording the current execution for later use and Fork, Restore, and Merge changing what the Agent will do next. An execution edit cannot undo an earlier authorization or a tool request already sent. An unsafe edit can therefore authorize the same tool action twice, discard a result the task still requires, or conflict with a call that began before the edit. The Agent is untrusted, so the runtime uses its execution record to determine which past actions an edit must account for and which required results it must preserve to keep the subsequent execution safe. Yet existing Agent systems support such operations without deriving what each edit must preserve from the running execution, whereas prior methods for computing safe behavior take that requirement as input. We give an algorithm that decides exactly whether an edit is safe. It returns all safe ways to continue, or proves that none exists. To make this decision, the algorithm lists every way the task can finish without violating policy. It removes any way that could make a still-required result impossible to finish later. If none remain, it returns a checkable proof that no safe implementation exists. Otherwise, the remaining ways describe exactly what the runtime may allow. Our formal results cover Checkpoint and the six forms of Fork, Restore, and Merge, together with extensions, atomic enforcement, and the information every exact checker needs. Lean mechanizes the finite checker and runtime invariant, and tests validate all six edit forms. The source code, Lean proofs, and executable tests are available in the public GitHub repository at https://github.com/eunomia-bpf/agent-check-restore-safety.

Quantum computers pose a fundamental threat to blockchain systems that rely on elliptic-curve cryptography. This work reviews the quantum vulnerabilities and associated economic risks of major blockchain platforms, with a focus on Bitcoin, Ethereum, and Solana. We distinguish between at-rest, on-spend, and on-setup attacks and identify the blockchain components most exposed to quantum adversaries. We further review practical migration strategies toward post-quantum security, including NIST-standardized digital signatures and emerging solutions for Solana, Algorand, and Ethereum.