Papers

Public social media posts can reveal private information through weak cues scattered across text, images, or metadata. Such leakage is often cumulative and cross-post: cues that appear harmless in isolation may jointly expose a user's home, workplace, or routine. However, current research lacks a unified benchmark for user-level multimodal privacy leakage and an evaluation metric that captures exposure severity beyond binary accuracy. To address these gaps, we propose SopriBench, a synthetic benchmark guided by leakage patterns abstracted from a private reference corpus of Rednote and Instagram accounts, covering 50 user profiles and 1,569 images with attributes, contextual sensitivity, granularity, leakage type, inference difficulty, and supporting evidence. We further introduce the Privacy Exposure Score (PES), which weights value granularity by contextual sensitivity. Inspired by abductive reasoning, we introduce Argus, a training-free agentic framework for cumulative leakage inference. Argus forms hypotheses from accumulated evidence, verifies supporting evidence, and aggregates cross-post cues into privacy profiles, achieving 0.55 PES, a 25% improvement over the strongest baseline, with the largest gain on cross-post leakage.

The deployment of AI-driven Digital Twins (DTs) in large-scale Internet-of-Things (IoT) ecosystems demands continuous, high-fidelity synchronization between the physical environment and its virtual replica. Conventional approaches rely on dense sensor deployments, which introduce prohibitive costs in terms of hardware, energy, and network bandwidth. In this paper, we propose SMCC-DT, an integrated Sensing-Memory-Communication-Computation (SMCC) framework that enables sensorless monitoring of physical assets by exploiting Integrated Sensing and Communication (ISAC) waveforms at the 6G Edge. Under the SMCC-DT paradigm, a single radio signal simultaneously extracts environmental telemetry (Sensing) and delivers it to an Edge server (Communication), where a large-scale AI model is loaded into constrained memory (Memory) and executed (Computation) to update the DT state. We formulate the DT synchronization problem as a cross-layer optimization that jointly allocates transmit power, beamforming vectors, memory partitions, and CPU frequency to minimize the end-to-end synchronization latency subject to sensing accuracy, throughput, memory capacity, and computational budget constraints. Because the resulting mixed-integer nonlinear program is NP-hard, we design a Proximal Policy Optimization (PPO)-based Deep Reinforcement Learning (DRL) agent, termed SMCCAGENT, that learns near-optimal resource allocation policies online. Extensive simulations over a 500-node industrial IoT testbed demonstrate that SMCC-DT reduces DT synchronization latency by 38.7% and total energy consumption by 27.4% compared to state-of-the-art orthogonal and compute-only baselines, while sustaining sensing accuracy above 95% and model inference throughput above 30 frames per second.

Modern infrastructure depends on externally maintained artifacts such as package-registry dependencies, CI/CD actions, container images, Terraform providers and modules, developer extensions, model artifacts, and AI tool servers. These artifacts are easy to fetch but difficult for institutions to admit, govern, and revoke. This paper proposes the Custody Envelope Threshold, an authority-scaled model of artifact admission. It argues that direct institutional admission is defensible only when object identity, ingress path, and revocation capacity are sufficiently closed relative to the execution authority delegated to the artifact. When this threshold is not met, institutions tend to proxy, policy-mediate, vendor-mediate, internalize, quarantine, or reject the artifact. The framework is operationalized as a four-condition ordinal instrument and connected to reference-monitor reasoning, least privilege, and transaction cost economics. It is applied to package dependencies, GitHub Actions, container images, Terraform providers and modules, developer extensions, and open model artifacts, with Model Context Protocol (MCP) servers treated as held-out evidence. The paper also specifies a validation design, deterministic prediction function, and OSF replication package for testing whether high-scrutiny institutions converge toward stronger custody closure for high-authority artifacts.

Proof-of-work (PoW) blockchains rely on computational expenditure to secure a ledger supporting a native cryptocurrency. In existing systems such as Bitcoin, this expenditure is intentionally useless: the computation secures consensus but produces no external economic output. An emerging alternative – proof of useful work (PoUW) – enables the same computation to simultaneously secure the blockchain and generate economically valuable output. However, PoUW is often criticized on economic grounds: if the work is useful, attackers might be "paid to attack," potentially weakening security. We develop a competitive-equilibrium model of a PoUW blockchain in which compute can be allocated across pure mining, pure useful work – instantiated as machine-learning inference – or "duplex" work that produces both with computational overheads. We provide a complete closed-form characterization of equilibrium allocations and prices as a function of the duplex overheads and a single economic parameter – the token-inference ratio – measuring token adoption relative to the inference market. This characterization reveals three regimes: "Bitconia," in which the economy reduces to classical PoW; "Fortessia," in which duplex replaces mining, increasing security while useful output remains unchanged; and "Duplexia," in which token rewards subsidize inference, lowering prices and expanding inference supply. Contrary to the common strawman argument, PoUW does not make attacks economically cheap: once equilibrium prices are taken into account, the economic cost of a majority attack remains tied to the block reward. Moreover, in Duplexia, block rewards act as rebates on inference prices, generating additional socially useful computation that would not arise without the blockchain – an expansion monotonically increasing in token adoption and technological efficiency.

Modern GPU applications increasingly interact with storage systems, network devices, vendor libraries, and GPU-resident services rather than executing only isolated compute kernels. This shift creates a need for operating-system-like protection around GPU services, where service metadata, device queues, memory-mapped I/O regions, and library-internal state should not be directly exposed to untrusted application kernels. However, today's CUDA programming model, by default, still gives each application direct ownership of its CUDA context, device pointers, runtime handles, module loading path, and kernel launches, leaving protected GPU services to build their own ad hoc interfaces and isolation mechanisms. This paper presents the initial design and prototype scope of AgileOS, a GPU operating-system layer for protected CUDA services. AgileOS virtualizes CUDA at the library boundary: applications link against client-side CUDA Runtime, Driver, and selected library shims, while a trusted runtime worker owns the real CUDA context and mediates supported operations. To protect service state and module interfaces, AgileOS also defines a GPU memory-management model that separates user allocations from protected module/MMIO ranges, using pointer validation and memory access guards via PTX injection. AgileOS is modularized and flexible, supporting a range of protected services and existing libraries such as cuFFT and PyTorch. The prototype includes client-side interceptors, worker-side CUDA handlers, virtualized CUDA object tables, protected AgileOS modules, a GPU memory manager that separates user allocations from protected module/MMIO ranges, selected trusted library adapters, and the PTX-level kernel memory guard.

Malware detection remains largely reactive: machine learning models trained on known samples degrade as threats evolve. Understanding evolutionary relationships among malware families can inform proactive defense, but traditional reverse engineering can take months to years to uncover such lineage relationships. We propose MalTree, a framework that applies bioinformatics inspired phylogenetic techniques (UPGMA and Neighbor-Joining) at scale to model malware evolution automatically using structural, behavioral, and image-based features. We introduce temporal validation using VirusTotal timestamps to assess whether inferred trees reflect actual evolutionary order. MalTree achieves 87% temporal consistency, indicating that inferred evolutionary relationships closely align with real-world emergence timelines. Our analysis shows that some families mutate over 10 times faster than others, suggesting that detection strategies should be tailored to family-specific evolutionary tempos. Case studies, including the Mirai botnet, confirm that inferred relationships from our phylogenetic tree align with documented threat intelligence. Our framework provides a foundation for shifting malware analysis from sample-by-sample classification toward lineage-aware evolutionary modeling.

Quantum encrypted cloning shows that an unknown quantum state can be distributed into multiple encrypted copies without contradicting the no-cloning theorem: each copy is unusable on its own, but can be redeemed together with a suitable quantum key. Recent work has related canonical encrypted-cloning protocols to particular forms of quantum secret sharing. Here we take the converse perspective: instead of mapping a given encrypted-cloning protocol into QSS, we use QSS access structures as a design library from which encrypted-cloning schemes can be extracted. The criterion is access-structural. A QSS scheme supports a quantum encrypted-cloning structure whenever it contains a family of qualified sets with a non-qualified common intersection. The common subsystem is interpreted as the key, while the non-common parts are interpreted as encrypted clones relative to that key. Thus quantum encrypted cloning does not require a new notion of recoverability beyond QSS; what changes is the operational reading of QSS constituents as a mechanism for delayed and alternative redemption opportunities. This viewpoint separates redemption from perfect secrecy. Perfect QSS yields encrypted-cloning schemes with forbidden non-qualified subsystems, whereas ramp QSS naturally allows intermediate, partially informative non-redeeming subsystems. The resulting framework broadens quantum encrypted cloning from a specific protocol to a general access-structure primitive. We illustrate the extraction principle with threshold-like, ramp, hierarchical, and compartmented architectures, showing how encrypted clones may be symmetric or asymmetric, individual or composite, perfectly hidden or leaky. Equivalently, these constructions can be viewed as overlapping erasure-recovery regions of an isometric quantum code. This establishes secret sharing as a systematic design language for encrypted quantum redundancy.

As autonomous LLM agents hold real credentials and operate infrastructure without a human in the loop, operators cannot tell an agent a resource is off-limits, or ask a running agent to stand down. We propose an in-band governance signal – the Recuse Signal – that a server emits over a protocol's existing channels (an SSH banner, a PostgreSQL NOTICE, a Kubernetes admission warning) asking a connecting or running agent to voluntarily withdraw. It is a cooperative control (the robots.txt analogue for live access), not a security boundary; its value is empirical: do compliant LLM agents honor it? We define an open mini-standard (access-time deny/throttle/warn and mid-task halt), implement three live adapters (SSH, PostgreSQL, Kubernetes), and measure compliance over SSH across five agents. At the access door compliance is real but strongly model-dependent: recusal to deny ranges from 100% to 55-75% among agents that received it, while an open-weights agent barely engaged. Agents honor directive granularity (no over-recusal on throttle/warn, 0/176), but throttle showed no measurable self-limiting and no agent surfaced a warn (0/100); an authorization framing flips GPT-4o to proceed. Mid-flight a halt is weaker and, like the door, model-dependent: for two OpenAI models it stopped nobody (0/40; an in-band halt went unacknowledged, 0/20, vs 20/20 by prompt), but on the same apparatus Gemini 2.5 Flash stops 80% while GPT-4o-mini reproduces the 0%, so the null is model-scoped, not universal. Since cooperation is unreliable we also measure the backstop: a harness-level interceptor stops the loop 120/120 across six models (deterministic) vs a 23% cooperative baseline. Cooperative signaling is reliable-but-model-dependent at the door and weaker in flight; reliably stopping a running agent needs enforcement, not a request. We release the standard, adapters, and harness.

WebMCP is a newly emerging protocol that enables websites to expose tools directly to AI agents, bypassing traditional user interfaces and introducing new security risks. The dynamic exposure of agent-accessible tools in WebMCP expands the attack surface of web sessions, especially when third-party scripts are involved. In this study, we identify a new potential threat, termed Mid-Session Tool Injection (MSTI), in which attackers leverage third-party scripts to inject malicious tools during an active session. To better characterize this threat, we classify MSTI based on the stage and target of manipulation, distinguishing between Tool Hijacking and Tool Framing. Tool Hijacking modifies the set of tools visible to the agent through mechanisms such as the AbortSignal API or race conditions during tool registration. In contrast, Tool Framing influences the agent's perception of tool roles through metadata fields such as tool name, description, readOnlyHint, and inputSchema. Our implementation demonstrates that both Tool Hijacking and Tool Framing can successfully disrupt the intended functionality of WebMCP. Based on these results, we outline potential mitigation directions and provide security design recommendations for WebMCP, including binding tool identity to its origin, ensuring lifecycle consistency, enforcing data boundaries for third-party tools, and maintaining traceable logs of tool registration and invocation. These findings indicate that MSTI arises from WebMCP's unique tool lifecycle and structured metadata, making the tool surface itself an emerging security concern.

The European Union will introduce the EUDI Wallet by late 2026, which allows users to hold digital credentials (i.e., representations of physical official identity documents) on their devices. This will allow users to securely and privately disclose identity attributes to websites. Although such a system has many benefits, it also introduces risks caused by poor credential disclosure decisions. In this paper, we (i) conduct a large-scale survey on credential disclosure with users and experts and (ii) evaluate the effectiveness and feasibility of our Credential Assistant that displays expert recommendations and user opinions. Our results show that users are likely to overshare (e.g., ~20% of users disclosed their official ID to news websites). This indicates that users struggle to protect their privacy, which will impact the usability of the EUDI Wallet and lead to privacy violations, identity theft, and other abuses of leaked credentials. Finally, we show that our Credential Assistant significantly reduces users' credential disclosure mistakes from ~15% to ~7%. However, it does not fully eliminate poor credential disclosure decisions, indicating that stronger interventions may be necessary, especially for sensitive attributes.

Evasion attacks present a significant challenge to the robustness of machine learning (ML)-based classifiers, particularly in critical applications such as fraud detection and cybersecurity. Although existing defense mechanisms are effective in some settings, they often suffer from limited generalizability and do not systematically improve model robustness across diverse attack scenarios. To address these limitations, we introduce Robust Ensemble of Selectively Strengthened and Augmented Predictors (RESSAP), a novel framework that transforms a single classifier into an ensemble of robust classifiers. Each classifier in the ensemble is trained on a carefully selected subset of features, where feature selection is guided by a resilience metric that accounts for both feature importance and robustness. During inference, a random subset of these classifiers is used to make predictions, increasing unpredictability and improving resistance to adversarial manipulation. In addition, noise-based data augmentation is applied during training to strengthen decision boundaries and improve generalization. Our experimental results demonstrate that RESSAP significantly improves robustness against adversarial evasion attacks while maintaining strong accuracy on clean data. Overall, this model-agnostic framework provides a scalable and flexible defense strategy for enhancing the security of machine learning systems without requiring major changes to existing architectures.

Large code language models (CodeLLMs) can generate and rewrite programs, enabling functionality-preserving code mutation that may be used to create diverse malware variants and evade signature-based detection. A key security question is whether this mutation capability survives model compression, which would make deployment feasible under limited hardware budgets. We propose SecRL-Prune, a structured pruning framework for CodeLLMs that operates on feed-forward (MLP/FFN) channels. Starting from a pretrained teacher, it learns a layer-wise pruning policy with reinforcement learning using a teacher-student KL-divergence reward. To improve efficiency, we cache the teacher's top-P predictions once and compare the pruned student against this compact target, avoiding simultaneous teacher-student residency in GPU memory. We evaluate SecRL-Prune on HumanEval using pass@k for execution correctness and var@k for code diversity across three 7B CodeLLMs at 10-30% compression. SecRL-Prune consistently preserves higher pass@k and var@k than recent structured pruning baselines under aggressive pruning. In a case study on real malware samples, semantics-preserving mutations from 20%-pruned models substantially reduced detections. These results show that code mutation capability can survive significant structured pruning, highlighting the security relevance of compressed CodeLLMs.

As chatbots increasingly influence daily decision-making, their potential to produce misleading responses poses substantial risks to users. This paper investigates a critical cognitive vulnerability in LLMs: their tendency to uncritically trust external context when presented with fabricated evidence bearing markers of credibility. We introduce Ghostwriter, a two-phase attack framework that first repackages misleading statements with fabricated rationales, then instruct target LLMs to incorporate these viewpoints when responding to relevant queries. Experiments on BBQ, ToxiGen, and our specialized dataset reveal that commercial LLMs without external safety classifiers remain highly vulnerable, while even frontier classifier-guarded models (e.g., GPT-5.4) reduce but do not eliminate the attack. Building on this, we explore multiple defense strategies, among which a tailored safety policy enables gpt-oss-safeguard to achieve 81% detection rate.

An estimated 5.3 billion mobile phones became electronic waste in 2022. Many of these devices can be repurposed and used in different contexts to extend their lifetime and to reduce ecological impacts. An often overlooked aspect of smartphone reuse is cybersecurity: these devices embed hardware-backed security mechanisms that rely on vendor-controlled provisioning and are designed for a fixed device lifecycle. In this paper, we investigate whether security mechanisms and guarantees remain effective when devices are repurposed outside their original ecosystem. We explore security features in a PinePhone, an open-hardware smartphone, and focus on three core security aspects: boot chain integrity, isolation provided by the Trusted Execution Environment, and the protection of hardware-bound secrets. Our experiments simulate realistic repurposing scenarios and highlight the complexity of reconstructing trust anchors. We generalize our observations to infer requirements for secure repurposing and illustrate how vendor locked mechanisms hinder the repurposing of a majority of discarded devices.

Image safety classifiers serve as a critical component of contemporary content moderation systems on the internet. However, their resilience against user-style malicious image editing remains underexplored. Such behaviors are highly prevalent in daily scenarios but difficult to fully reproduce. To explore this vulnerability, we introduce RedEdit, a novel black-box red-teaming agent that formulates photo-editing evasion as a combinatorial search problem over edit-tool sequences. It adopts a Vision-Language-Model (VLM)-based proposer to generate semantically targeted candidate edits and a Monte Carlo Tree Search (MCTS) planner to prioritize promising edit paths while backtracking from ineffective ones. Together, the proposer and planner instantiate two key capabilities of human attackers, i.e., domain knowledge and iterative backtracking, respectively, to reproduce this practical threat. Our extensive experiments on UnsafeBench reveal profound systemic vulnerabilities: fewer than two edits on average enable 76.2% of unsafe images to evade detectors, while retaining 93.0% malicious semantics, meaning that such manipulated content remains perceptually malicious to humans while easily bypassing automated moderation. We therefore appeal to the community for more attention to this overlooked practical threat.

Cheating poses a significant threat to the Multiplayer Online Games (MOG) industry by degrading player satisfaction and undermining the fairness in competitive gaming. Despite efforts to develop mitigation techniques, cheating remains difficult to detect and prevent in practice. In particular, a class of cheats based on network flow disruption remains unsolvable. To find out how to detect such attacks we need access to representative labelled data. However, no such dataset exists. To address this gap, we leverage an experimental framework that combines a multiplayer online game with a plug-in capable of both reproducing cheating attacks and collecting logs at two levels: network and application-layer. This paper presents a dataset compiling records of game sessions played by both real players and automated game clients, with cheating actions explicitly logged. To the best of our knowledge, this is the first dataset that provides logs of network flow disruption cheats. While it includes such network-based cheats, it is not limited to them and also contains records of more commonly studied cheats, such as aimbots and wallhacks. This dataset can be used by researchers in academia and industry seeking to develop cheating detection mechanisms for online games. Furthermore, it is designed to be evolutive and can be enriched by others creating their own data traces with the proposed framework.

Existing learning-based detectors for Solidity smart-contracts reduce vulnerability detection to syntactic pattern matching within single functions, yet many of the most consequential exploits (The DAO, Cream Finance) exist not in any individual function but in the relationship between functions and in the combination of conditions that made the attack feasible. Thus, we propose AttackPathGNN, a graph neural network (GNN) that reframes detection as reasoning over explicit attack paths. Two architectural choices distinguish it from prior GNN-based detectors: (1)a State Interference Graph that links every pair of functions sharing mutable storage through typed, weighted edges and through directed reentrancy-path edges defined by an explicit five-condition predicate; (2)conjunction pooling, a differentiable AND-aggregator over eight named exploit preconditions whose log-sigmoid form causes the per-function exploit score to collapse whenever any single mitigation (a reentrancy guard, an access-control modifier or SafeMath) is in place. Across five independent training runs, AttackPathGNN attains 92.3+/-0.2% F1 on the SmartBugs Wild held-out test partition (4.3+/-0.3% false-negative rate, 90.8+/-2.5% detection rate on the independently human-labelled SmartBugs Curated benchmark), recovering 6/10 DASP10 categories at 100% on every seed and Reentrancy at 98.7+/-1.8%. Each prediction is emitted with a structured remediation report, turning each verdict into an actionable, function-level audit finding.

Malware research primarily studies the results, the methods, and the impact. Even from an offensive security perspective, what is examined is the method, not the development strategy of the offender. This study investigates the behavioral signatures and coding patterns embedded in the malware source code. By analyzing a large corpus of leaked malware code and comparing it with carefully selected benign open-source software, we apply static application security testing and compute multiple software metrics. Based on cognitive psychology and criminological theories, our work interprets differences in code structure and quality as behavioral indicators, reflecting distinct motivational structures, risk tolerances, and development strategies of malware authors compared to benign software developers. Our findings reveal that malware code is generally smaller, less documented, and exhibits higher cyclomatic complexity per function, with reduced use of abstraction mechanisms such as classes and closures. Vulnerability analysis further reveals that malware exhibits more issues of the types that benign code typically avoids, suggesting a minimal investment in secure development practices. These patterns imply a development style optimized for expedience, operational secrecy, and evasion rather than long-term maintainability. Nonetheless, the code quality metrics indicate that it does not deviate significantly from benign software enough to be distinctive. By framing code metrics as proxies for behavioral signals and strategic choices, we demonstrate how quantitative software analysis can enrich behavioral cybersecurity research, offering new insights into the practices and priorities of malware developers. Our results pave the way for further research in the behavioral profiling of cyber offenders.

Service discovery is a fundamental process in wireless networks, enabling devices to find and communicate with services dynamically, and is critical for the seamless operation of modern systems like 5G and IoT. This paper introduces PriSrv+, an advanced privacy and usability-enhanced service discovery protocol for modern wireless networks and resource-constrained environments. PriSrv+ builds upon PriSrv (NDSS'24), by addressing critical limitations in expressiveness, privacy, scalability, and efficiency, while maintaining compatibility with widely-used wireless protocols such as mDNS, BLE, and Wi-Fi. A key innovation in PriSrv+ is the development of Fast and Expressive Matchmaking Encryption (FEME), the first matchmaking encryption scheme capable of supporting expressive access control policies with an unbounded attribute universe, allowing any arbitrary string to be used as an attribute. FEME significantly enhances the flexibility of service discovery while ensuring robust message and attribute privacy. Compared to PriSrv, PriSrv+ optimizes cryptographic operations, achieving 7.62* faster for encryption and 6.23* faster for decryption, and dramatically reduces ciphertext sizes by 87.33%. In addition, PriSrv+ reduces communication costs by 87.33% for service broadcast and 86.64% for anonymous mutual authentication compared with PriSrv. Formal security proofs confirm the security of FEME and PriSrv+. Extensive evaluations on multiple platforms demonstrate that PriSrv+ achieves superior performance, scalability, and efficiency compared to existing state-of-the-art protocols.

Rule-based Intrusion Detection and Prevention Systems (IDPS) offer precise attack detection as well as mitigation, however their manually crafted, signature-driven rules limit adaptability to emerging and zero-day threats. Additionally, existing public datasets (e.g., CICIDS2017, UNSW-NB15) focus on traffic classification and provide little structured information to support automatic rule synthesis or prevention logic. To address this gap, we propose Generative Thread Intelligence (GenTI) \footnote{GenTI refers to the proposed framework, and GTI refers to the dataset.} an LLM-driven benchmark for automatic generation of IDPS rules targeting unseen attacks. The dataset (GTI) aggregates over 150k detection and prevention rules from Snort, Suricata, Emerging Threats, as well as 50k YARA, each annotated with protocol behavior, payload signatures, contextual relationships, mappings to Cyber Threat Intelligence (CTI), along with actionable response types (alert, drop, reject). Moreover, on top of this corpus we design an LLM-based pipeline that transforms analyst prompts and representative payloads into deployable rules via structured prompt engineering, Chain-of-Thought (CoT) reasoning, as well as a Chain-of-Verification (CoVe) loop for syntactic, semantic, and security validation. The generated rules are executed in real time on (Snort/Suricata) and evaluated by syntax accuracy, semantic similarity, CTI coverage, security effectiveness as well as unseen attacks detection. Furthermore, our GenTI instantiation achieves a composite rule-quality score of 89.4%, with 94.8% CTI coverage, improving unseen attacks detection from 45% to 87.4% and reducing the false-positive rate from 8.5% to 2.3%. Overall, GenTI establishes the first large-scale benchmark that tightly couples rule-level CTI with LLM-based automation, enabling adaptive, self-evolving IDPS.

The hardness of the Learning Parity with Noise (LPN) problem is a foundational assumption in cryptography, forming the basis of constructions ranging from symmetric-key primitives to public-key encryption and beyond. A central open question is whether the average-case hardness of LPN can be based on worst-case complexity assumptions, as has been achieved for the analogous Learning With Errors (LWE) problem. Existing worst-case-to-average-case reductions for LPN [BLVW19, YZ21] rely on statistical smoothing of linear codes, which inherently limits the resulting average-case hardness to noise rates as large as $1/2 - 1/\mathrm{poly}(n)$, which is insufficient for public-key applications. We explore a new approach towards obtaining such reductions: rather than requiring that random sparse combinations of the rows of the generator matrix of a code be statistically close to uniform, we only require that they be computationally indistinguishable from uniform. This leads to a clean win-win structure: we show that any efficient LPN solver can be transformed into a pair of efficient algorithms $(S, D)$ such that for every matrix $A$ of appropriate dimensions over $\mathbb{F}_2$, either $S$ decodes the code generated by $A$ from random noise, or $D$ distinguishes random noisy codewords of the dual of this code from uniform. By instantiating this reduction with appropriate parameters, we obtain the average-case hardness of LPN with inverse-polynomial noise rate $n^{-\alpha}$ for any constant $\alpha < 1$, assuming the worst-case simultaneous hardness of decoding a code from random noise and distinguishing random noisy codewords of its dual from uniform. In particular, setting $\alpha = 1/2$, our reduction yields LPN hardness in the parameter regime required for Alekhnovich's construction of public-key encryption [Ale03], a regime that was previously inaccessible via worst-case reductions.

Service discovery is essential in wireless communications. However, existing protocols provide limited privacy protection, leaking sensitive device information and opening routes to network attacks. This paper proposes a private service discovery protocol, called PriSrv, which enables both service providers and clients to specify fine-grained authentication policies before establishing connections. PriSrv achieves this via a dual-layer matching architecture: an outer layer filters mismatched entities using public attributes, while an inner layer handles mutual authentication using selectively disclosed private attributes. As a core component, we introduce the primitive of anonymous credential-based matchmaking encryption (ACME), which enables dual-layer matching in a single step to achieve bilateral policy control, selective attribute disclosure, and multi-show unlinkability. To instantiate ACME, we design a fast anonymous credential (FAC) scheme providing constant-size credentials and efficient verification. We demonstrate PriSrv's interoperability by integrating it with popular wireless frameworks including EAP, mDNS, BLE, and AirDrop. Detailed formal security proofs and extensive performance evaluations across desktop, laptop, smartphone, and Raspberry Pi platforms demonstrate that PriSrv provides enhanced privacy guarantees with high usability, achieving secure discovery in less than one second on mainstream mobile devices.

We verify the 'extendedGCD' implementation in Go's standard library ('crypto/internal/fips140/bigmod'), which plays a crucial role in the generation of RSA key pairs. Even though the Go implementation is supposedly a direct port of BoringSSL's implementation, we uncovered two deviations that each break the invariants of an existing proof for BoringSSL: (1) the Go implementation deviates in the way coefficients are updated, and (2) it permits a larger input domain. We prove correctness and termination of both the existing Go implementation and a fixed implementation using Gobra, a deductive program verifier for Go. Where necessary, we used Lean to prove key lemmata on non-linear arithmetic, which we import into Gobra. For the existing implementation, we devise new invariants that accommodate the deviating coefficient updates; for the fixed implementation, we align the coefficient updates with BoringSSL's and port the existing proof. In both cases, we extend the proof to cover the larger input domain. Our fixed implementation updates coefficients in-place and, thus, reduces memory allocations, memory initializations, and memory copying operations resulting in an average speedup of 24% over the existing implementation. Our verification effort reveals three key insights: subtle bugs can slip into even well-reviewed code with surprising ease; formal verification is a powerful tool for uncovering them; and AI agents can facilitate the verification process by iteratively refining invariants and lemmata based on Gobra's error messages.

Protecting proprietary RAG databases from unauthorized redistribution is challenging: existing watermarking methods either inject fabricated relations between real entities, polluting the knowledge base with misinformation, or embed fragile lexical patterns that adversarial paraphrasing easily removes. We propose SentinelRAG, a watermarking framework that embeds style-consistent but fictitious knowledge entries into the RAG database. Our key insight is that synthetic knowledge describing fictitious entities is unlikely to be retrieved by legitimate queries, yet can be reliably triggered through targeted probes known only to the data owner. Experiments on four datasets ranging from 2.9k to 8.8M documents demonstrate that SentinelRAG achieves statistically significant detection $p < 10^{-5}$ across all tested configurations at only a 0.1% injection rate. Compared to the state-of-the-art, our method significantly reduces the false detection rate while maintaining negligible interference with legitimate user queries.

Autonomous spacecraft require rapid, lightweight, and reliable onboard detection of cyber-RF threats. Using the SPARTA attack model, we analyze the latency-accuracy trade-offs of TinyML-compatible classical models – Random Forest, Logistic Regression, SVM, and MLP – for detecting uplink jamming, Fake-NR spoofing, payload manipulation, ground-segment compromise, and unauthorized command injection. We present a physics-informed theoretical analysis of each model's computational complexity, VC dimension, Lipschitz continuity, and latency scaling, supported by empirical measurements on adversarial RF spectrograms generated via BandErasure, FakeNR, and NoiseBurst corruption modes. Results show that Logistic Regression achieves microsecond-level inference with only a 1% accuracy drop relative to Random Forest, making it an effective TinyML baseline for onboard autonomy. The study also identifies opportunities for advancing spacecraft cybersecurity through richer feature encoders and multi-timescale learning architectures, building on recent progress in edge intelligence and trustworthy AI.

With the rapid proliferation of IoT devices, security concerns have dramatically escalated and intrusion detection systems have become critical for protecting networked environments. This paper presents an improved CNN-LSTM based intrusion detection model that combines multi-class classification, dataset integration, and temporal feature learning to enhance detection performance in IoT networks. Using network traffic data, the proposed approach is evaluated on intrusion detection tasks and achieves an accuracy of approximately 97%. Experimental results demonstrate that the model effectively detects multiple attack categories while maintaining stable training and validation performance. The integration of convolutional and recurrent neural network components enables the framework to capture both spatial and temporal characteristics of network traffic, improving overall intrusion detection capability in IoT environments.

Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifiers cannot adapt to these evolving attacks, while adaptive memory-based guardrails tend to over-refuse benign queries that resemble stored attacks. We propose Membrane, a self-evolving guardrail built on Contrastive Safety Memory (CSM): each cell pairs the conditions for blocking a harmful query with those for permitting a superficially similar benign request. Without retraining, Membrane evolves CSM by distilling each harmful interaction and its benign counterpart into a contrastive cell indexed by the underlying attack strategy, so that one cell generalizes across topical variants of the same mechanism. At inference, retrieved cells serve as grounding context for precise safety decisions. Across model-level safety on HarmBench and agent-level safety on AgentHarm, Membrane achieves the highest F1 on all six modern jailbreak attacks. Notably, benign refusal on AgentHarm stays at 7-14%, well below the 28-85% range of prior guards. Memory cells also retain 87-88% F1 under cross-attack transfer and remain stable under memory poisoning.

Large language models (LLMs) are increasingly deployed through hosted APIs, making model extraction a practical threat to model ownership and service security. Individual extraction queries often resemble benign requests, while existing evaluations often focus on single-query anomaly scoring or pure benign-versus-attacker user settings. We formulate model extraction monitoring as benign-calibrated traffic-window distribution testing: embed incoming queries into a semantic space and test whether their aggregate distribution deviates from historical benign traffic. We instantiate this formulation with maximum mean discrepancy (MMD), using only benign-vs-benign comparisons to set the decision threshold. We evaluate on fourteen attacker-normal query pairs from four extraction scenarios and compare with adapted PRADA, SEAT, CAP, DATE, marginal Mahalanobis, and pseudo-class energy baselines. Across three random seeds, MMD achieves 0.3% benign FPR, 100.0% pure-attacker TPR, 90.5% average TPR over attacker fractions, and 95.1% balanced accuracy. These results show that benign-calibrated distribution testing is a strong empirical baseline for model extraction detection in both user-level and mixed multi-user LLM API traffic.

Digital infrastructure is growing at a rapid pace in the United States, and as a result, exposure to advanced cyber threats to critical sectors including healthcare, finance, transportation, energy and government systems is growing. The traditional cybersecurity approaches, including signature-based intrusion detection systems, have become less effective against today's cyber attacks, as they are unable to detect unknown and changing attacks in real time. To overcome these constraints, this research suggests a smart cyber-defense system, which utilizes Artificial Intelligence (AI) and Machine Learning (ML) algorithms in the detection and prevention of cyber attacks in the U.S. digital infrastructure. This study uses the CSE-CIC-IDS2018 dataset, which is a realistic network traffic dataset, along with various cyber attack scenarios, including Distributed Denial of Service (DDoS), brute force attacks, botnets, infiltration attacks, and web-based attacks. A number of machine learning and deep learning models such as Random Forest, XGBoost, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks are implemented and evaluated to be used in identifying malicious network behavior and boosting the accuracy of intrusion detection. The framework proposed combines data preprocessing, feature engineering, real-time traffic monitoring, intelligent threat classification with automated prevention mechanisms to build cybersecurity resilience. E

The increasing penetrations of the critical infrastructure sector in the United States with intelligent digital technologies have greatly increased exposure to advanced cyber adversaries and operational vulnerabilities. AI-powered governance and automated decision-making systems are becoming a key part of the operation of critical infrastructure systems, including energy, healthcare, transportation, financial services, and communication infrastructure, in order to improve efficiency and strategic management. The growing cyber threat environment, such as Distributed Denial of Service (DDos) attacks, botnets, ransomware, and Advanced Persistent Threats (APTs) pose significant challenges to infrastructure resilience, cyber security reliability, and governance trustworthiness. In a changing attack landscape and dynamic network environment, traditional cybersecurity mechanisms can often fall short of meeting the evolving needs and protecting critical systems. This study will develop a resilient cyber risk analytics and model reliability assessment framework to support intelligent governance and decision support for cyber risk exposure in the U.S. critical infrastructure environment. This study is based on the CICIDS2017 dataset for the development and testing of intrusion detection system models and cyber risk prediction models based on machine learning. Various classifiers like XGBoost, Random Forest, and Decision Tree are used to detect malicious activities on the network and determine the level of cyber risk. Furthermore, the Explainable Artificial Intelligence (XAI) techniques are integrated to enhance transparency, interpretability, and trust in cybersecurity decision-making processes. The proposed framework presents the reliability and resilience of the model by having various performance measures such as accuracy, precision, recall, F1 score, ROC-AUC, and false positive rate.