Papers

Key-length extension (KLE) techniques provide a general approach to enhancing the security of block ciphers by using longer keys. There are mainly two classes of KLE techniques, cascade encryption and XOR-cascade encryption. This paper presents several quantum meet-in-the-middle (MITM) attacks against two specific KLE constructions. For the two-key triple encryption (2kTE), we propose two quantum MITM attacks under the Q2 model. The first attack, leveraging the quantum claw-finding (QCF) algorithm, achieves a time complexity of $O(2^{2\kappa/3})$ with $O(2^{2\kappa/3})$ quantum random access memory (QRAM). The second attack, based on Grover's algorithm, achieves a time complexity of $O(2^{\kappa/2})$ with $O(2^\kappa)$ QRAM. The latter complexity is nearly identical to Grover-based brute-force attack on the underlying block cipher, indicating that 2kTE does not enhance security under the Q2 model when sufficient QRAM resources are available. For the 3XOR-cascade encryption (3XCE), we propose a quantum MITM attack applicable to the Q1 model. This attack requires no QRAM and has a time complexity of $O(2^{(\kappa+n)/2})$ ($\kappa$ and $n$ are the key length and block length of the underlying block cipher, respectively.), achieving a quadratic speedup over classical MITM attack. Furthermore, we extend the quantum MITM attack to quantum sieve-in-the-middle (SITM) attack, which is applicable for more constructions. We present a general quantum SITM framework for the construction $ELE=E^2\circ L\circ E^1$ and provide specific attack schemes for three different forms of the middle layer $L$. The quantum SITM attack technique can be further applied to a broader range of quantum cryptanalysis scenarios.

We consider the problem of certified robustness for sequence classification against edit distance perturbations. Naturally occurring inputs of varying lengths (e.g., sentences in natural language processing tasks) present a challenge to current methods that employ fixed-rate deletion mechanisms and lead to suboptimal performance. To this end, we introduce AdaptDel methods with adaptable deletion rates that dynamically adjust based on input properties. We extend the theoretical framework of randomized smoothing to variable-rate deletion, ensuring sound certification with respect to edit distance. We achieve strong empirical results in natural language tasks, observing up to 30 orders of magnitude improvement to median cardinality of the certified region, over state-of-the-art certifications.

Modern enterprise networks comprise diverse and heterogeneous systems that support a wide range of services, making it challenging for administrators to track and analyze sophisticated attacks such as advanced persistent threats (APTs), which often exploit multiple vectors. To address this challenge, we introduce the concept of network-level security provenance, which enables the systematic establishment of causal relationships across hosts at the network level, facilitating the accurate identification of the root causes of security incidents. Building on this concept, we present SecTracer as a framework for a network-wide provenance analysis. SecTracer offers three main contributions: (i) comprehensive and efficient forensic data collection in enterprise networks via software-defined networking (SDN), (ii) reconstruction of attack histories through provenance graphs to provide a clear and interpretable view of intrusions, and (iii) proactive attack prediction using probabilistic models. We evaluated the effectiveness and efficiency of SecTracer through a real-world APT simulation, demonstrating its capability to enhance threat mitigation while introducing less than 1% network throughput overhead and negligible latency impact.

This chapter explores how Decentralized Autonomous Organizations (DAOs), a novel institutional form based on blockchain technology, challenge traditional centralized governance structures. DAOs govern projects ranging from finance to science and digital communities. They aim to redistribute decision-making power through programmable, transparent, and participatory mechanisms. This chapter outlines both the opportunities DAOs present, such as incentive alignment, rapid coordination, and censorship resistance, and the challenges they face, including token concentration, low participation, and the risk of de facto centralization. It further discusses the emerging intersection of DAOs and artificial intelligence, highlighting the potential for increased automation alongside the dangers of diminished human oversight and algorithmic opacity. Ultimately, we discuss under what circumstances DAOs can fulfill their democratic promise or risk replicating the very power asymmetries they seek to overcome.

Traditional distributed backdoor attacks (DBA) in federated learning improve stealthiness by decomposing global triggers into sub-triggers, which however requires more poisoned data to maintian the attck strength and hence increases the exposure risk. To overcome this defect, This paper proposes a novel method, namely Fractal-Triggerred Distributed Backdoor Attack (FTDBA), which leverages the self-similarity of fractals to enhance the feature strength of sub-triggers and hence significantly reduce the required poisoning volume for the same attack strength. To address the detectability of fractal structures in the frequency and gradient domains, we introduce a dynamic angular perturbation mechanism that adaptively adjusts perturbation intensity across the training phases to balance efficiency and stealthiness. Experiments show that FTDBA achieves a 92.3% attack success rate with only 62.4% of the poisoning volume required by traditional DBA methods, while reducing the detection rate by 22.8% and KL divergence by 41.2%. This study presents a low-exposure, high-efficiency paradigm for federated backdoor attacks and expands the application of fractal features in adversarial sample generation.

Smart contracts have significantly advanced blockchain technology, and digital signatures are crucial for reliable verification of contract authority. Through signature verification, smart contracts can ensure that signers possess the required permissions, thus enhancing security and scalability. However, lacking checks on signature usage conditions can lead to repeated verifications, increasing the risk of permission abuse and threatening contract assets. We define this issue as the Signature Replay Vulnerability (SRV). In this paper, we conducted the first empirical study to investigate the causes and characteristics of the SRVs. From 1,419 audit reports across 37 blockchain security companies, we identified 108 with detailed SRV descriptions and classified five types of SRVs. To detect these vulnerabilities automatically, we designed LASiR, which utilizes the general semantic understanding ability of Large Language Models (LLMs) to assist in the static taint analysis of the signature state and identify the signature reuse behavior. It also employs path reachability verification via symbolic execution to ensure effective and reliable detection. To evaluate the performance of LASiR, we conducted large-scale experiments on 15,383 contracts involving signature verification, selected from the initial dataset of 918,964 contracts across four blockchains: Ethereum, Binance Smart Chain, Polygon, and Arbitrum. The results indicate that SRVs are widespread, with affected contracts holding $4.76 million in active assets. Among these, 19.63% of contracts that use signatures on Ethereum contain SRVs. Furthermore, manual verification demonstrates that LASiR achieves an F1-score of 87.90% for detection. Ablation studies and comparative experiments reveal that the semantic information provided by LLMs aids static taint analysis, significantly enhancing LASiR's detection performance.

Multiple-Criteria Decision Making (MCDM) is a sub-discipline of Operations Research that helps decision-makers in choosing, ranking, or sorting alternatives based on conflicting criteria. Over time, its application has been expanded into dynamic and data-driven domains, such as recommender systems. In these contexts, the availability and handling of personal and sensitive data can play a critical role in the decision-making process. Despite this increased reliance on sensitive data, the integration of privacy mechanisms with MCDM methods is underdeveloped. This paper introduces an integrated approach that combines MCDM outranking methods with Differential Privacy (DP), safeguarding individual contributions' privacy in ranking problems. This approach relies on a pre-processing step to aggregate multiple user evaluations into a comprehensive performance matrix. The evaluation results show a strong to very strong statistical correlation between the true rankings and their anonymized counterparts, ensuring robust privacy parameter guarantees.

Recent advances in deep reinforcement learning for autonomous cyber defence have resulted in agents that can successfully defend simulated computer networks against cyber-attacks. However, many of these agents would need retraining to defend networks with differing topology or size, making them poorly suited to real-world networks where topology and size can vary over time. In this research we introduce a novel set of Topological Extensions for Reinforcement Learning Agents (TERLA) that provide generalisability for the defence of networks with differing topology and size, without the need for retraining. Our approach involves the use of heterogeneous graph neural network layers to produce a fixed-size latent embedding representing the observed network state. This representation learning stage is coupled with a reduced, fixed-size, semantically meaningful and interpretable action space. We apply TERLA to a standard deep reinforcement learning Proximal Policy Optimisation (PPO) agent model, and to reduce the sim-to-real gap, conduct our research using Cyber Autonomy Gym for Experimentation (CAGE) Challenge 4. This Cyber Operations Research Gym environment has many of the features of a real-world network, such as realistic Intrusion Detection System (IDS) events and multiple agents defending network segments of differing topology and size. TERLA agents retain the defensive performance of vanilla PPO agents whilst showing improved action efficiency. Generalisability has been demonstrated by showing that all TERLA agents have the same network-agnostic neural network architecture, and by deploying a single TERLA agent multiple times to defend network segments with differing topology and size, showing improved defensive performance and efficiency.

Current adversarial examples (AEs) are typically designed for static models. However, with the wide application of Class-Incremental Learning (CIL), models are no longer static and need to be updated with new data distributed and labeled differently from the old ones. As a result, existing AEs often fail after CIL updates due to significant domain drift. In this paper, we propose SAE to enhance the sustainability of AEs against CIL. The core idea of SAE is to enhance the robustness of AE semantics against domain drift by making them more similar to the target class while distinguishing them from all other classes. Achieving this is challenging, as relying solely on the initial CIL model to optimize AE semantics often leads to overfitting. To resolve the problem, we propose a Semantic Correction Module. This module encourages the AE semantics to be generalized, based on a visual-language model capable of producing universal semantics. Additionally, it incorporates the CIL model to correct the optimization direction of the AE semantics, guiding them closer to the target class. To further reduce fluctuations in AE semantics, we propose a Filtering-and-Augmentation Module, which first identifies non-target examples with target-class semantics in the latent space and then augments them to foster more stable semantics. Comprehensive experiments demonstrate that SAE outperforms baselines by an average of 31.28% when updated with a 9-fold increase in the number of classes.

Edge computing pushes computation closer to data sources, but it also expands the attack surface on resource-constrained devices. This work explores the deployment of the Lightweight Deep Anomaly Detection for Network Traffic (LDPI) integrated as an isolated service within a virtualization framework that provides security by separation. LDPI, adopting a Deep Learning approach, achieved strong training performance, reaching AUC 0.999 (5-fold mean) across the evaluated packet-window settings (n, l), with high F1 at conservative operating points. We deploy LDPI on a laptop-class edge node and evaluate its overhead and performance in two scenarios: (i) comparing it with representative signature-based IDSes (Suricata and Snort) deployed on the same framework under identical workloads, and (ii) while detecting network flooding attacks.

Smart contracts concentrate high value assets and complex logic in small, immutable programs, where even minor bugs can cause major losses. Existing taxonomies and tools remain fragmented, organized around symptoms such as reentrancy rather than structural causes. This paper introduces an attack-centric, program-structure taxonomy that unifies Solidity vulnerabilities into eight root-cause families covering control flow, external calls, state integrity, arithmetic safety, environmental dependencies, access control, input validation, and cross-domain protocol assumptions. Each family is illustrated through concise Solidity examples, exploit mechanics, and mitigations, and linked to the detection signals observable by static, dynamic, and learning-based tools. We further cross-map legacy datasets (SmartBugs, SolidiFI) to this taxonomy to reveal label drift and coverage gaps. The taxonomy provides a consistent vocabulary and practical checklist that enable more interpretable detection, reproducible audits, and structured security education for both researchers and practitioners.

Healthcare federated learning requires strong privacy guarantees while maintaining computational efficiency across resource-constrained medical institutions. This paper presents MedHE, a novel framework combining adaptive gradient sparsification with CKKS homomorphic encryption to enable privacy-preserving collaborative learning on sensitive medical data. Our approach introduces a dynamic threshold mechanism with error compensation for top-k gradient selection, achieving 97.5 percent communication reduction while preserving model utility. We provide formal security analysis under Ring Learning with Errors assumptions and demonstrate differential privacy guarantees with epsilon less than or equal to 1.0. Statistical testing across 5 independent trials shows MedHE achieves 89.5 percent plus or minus 0.8 percent accuracy, maintaining comparable performance to standard federated learning (p=0.32) while reducing communication from 1277 MB to 32 MB per training round. Comprehensive evaluation demonstrates practical feasibility for real-world medical deployments with HIPAA compliance and scalability to 100 plus institutions.

Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing model stealing attacks, and make it difficult for model owners to effectively verify the copyright of stolen models. In this paper, we analyze the root cause of the failure of current watermarking methods under model stealing scenarios and then explore potential solutions. Specifically, we introduce a robust watermarking framework, DeepTracer, which leverages a novel watermark samples construction method and a same-class coupling loss constraint. DeepTracer can incur a high-coupling model between watermark task and primary task that makes adversaries inevitably learn the hidden watermark task when stealing the primary task functionality. Furthermore, we propose an effective watermark samples filtering mechanism that elaborately select watermark key samples used in model ownership verification to enhance the reliability of watermarks. Extensive experiments across multiple datasets and models demonstrate that our method surpasses existing approaches in defending against various model stealing attacks, as well as watermark attacks, and achieves new state-of-the-art effectiveness and robustness.

Backdoor attacks pose a critical threat to machine learning models, causing them to behave normally on clean data but misclassify poisoned data into a poisoned class. Existing defenses often attempt to identify and remove backdoor neurons based on Trigger-Activated Changes (TAC) which is the activation differences between clean and poisoned data. These methods suffer from low precision in identifying true backdoor neurons due to inaccurate estimation of TAC values. In this work, we propose a novel backdoor removal method by accurately reconstructing TAC values in the latent representation. Specifically, we formulate the minimal perturbation that forces clean data to be classified into a specific class as a convex quadratic optimization problem, whose optimal solution serves as a surrogate for TAC. We then identify the poisoned class by detecting statistically small $L^2$ norms of perturbations and leverage the perturbation of the poisoned class in fine-tuning to remove backdoors. Experiments on CIFAR-10, GTSRB, and TinyImageNet demonstrated that our approach consistently achieves superior backdoor suppression with high clean accuracy across different attack types, datasets, and architectures, outperforming existing defense methods.

Given the high cost of large language model (LLM) training from scratch, safeguarding LLM intellectual property (IP) has become increasingly crucial. As the standard paradigm for IP ownership verification, LLM fingerprinting thus plays a vital role in addressing this challenge. Existing LLM fingerprinting methods verify ownership by extracting or injecting model-specific features. However, they overlook potential attacks during the verification process, leaving them ineffective when the model thief fully controls the LLM's inference process. In such settings, attackers may share prompt-response pairs to enable fingerprint unlearning or manipulate outputs to evade exact-match verification. We propose iSeal, the first fingerprinting method designed for reliable verification when the model thief controls the suspected LLM in an end-to-end manner. It injects unique features into both the model and an external module, reinforced by an error-correction mechanism and a similarity-based verification strategy. These components are resistant to verification-time attacks, including collusion-based fingerprint unlearning and response manipulation, backed by both theoretical analysis and empirical results. iSeal achieves 100 percent Fingerprint Success Rate (FSR) on 12 LLMs against more than 10 attacks, while baselines fail under unlearning and response manipulations.

Ultra-low latency, the hallmark of fifth-generation mobile communications (5G), imposes exacting timing demands on identification as well. Current cryptographic solutions introduce additional computational overhead, which results in heightened identification delays. Radio frequency fingerprint (RFF) identifies devices at the physical layer, blocking impersonation attacks while significantly reducing latency. Unfortunately, multipath channels compromise RFF accuracy, and existing channel-resilient methods demand feedback or processing across multiple time points, incurring extra signaling latency. To address this problem, the paper introduces a new RFF extraction technique that employs signals from multiple receiving antennas to address multipath issues without adding latency. Unlike single-domain methods, the Log-Linear Delta Ratio (LLDR) of co-temporal channel frequency responses (CFRs) from multiple antennas is employed to preserve discriminative RFF features, eliminating multi-time sampling and reducing acquisition time. To overcome the challenge of the reliance on minimal channel variation, the frequency band is segmented into sub-bands, and the LLDR is computed within each sub-band individually. Simulation results indicate that the proposed scheme attains a 96.13% identification accuracy for 30 user equipments (UEs) within a 20-path channel under a signal-to-noise ratio (SNR) of 20 dB. Furthermore, we evaluate the theoretical latency using the Roofline model, resulting in the air interface latency of 0.491 ms, which satisfies ultra-reliable and low-latency communications (URLLC) latency requirements.

AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety mechanisms, security vulnerabilities and challenges have become increasingly prevalent in this domain, posing a significant barrier to the practical deployment and safety of AI systems. This paper proposes an agentic AI safety architecture that leverages 3D to integrate a dedicated safety layer. It introduces an adaptive AI safety infrastructure capable of dynamically learning and mitigating attacks against the AI system. The system leverages the inherent advantages of co-location with the edge computing hardware to continuously monitor, detect and proactively mitigate threats to the AI system. The integration of local processing and learning capabilities enhances resilience against emerging network-based attacks while simultaneously improving system reliability, modularity, and performance, all with minimal cost and 3D integration overhead.

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both noise and bias. Existing techniques typically address only one of these issues, as reducing DP noise can exacerbate clipping bias and vice-versa. In this paper, we propose a novel method, DP-PMLF, which integrates per-sample momentum with a low-pass filtering strategy to simultaneously mitigate DP noise and clipping bias. Our approach uses per-sample momentum to smooth gradient estimates prior to clipping, thereby reducing sampling variance. It further employs a post-processing low-pass filter to attenuate high-frequency DP noise without consuming additional privacy budget. We provide a theoretical analysis demonstrating an improved convergence rate under rigorous DP guarantees, and our empirical evaluations reveal that DP-PMLF significantly enhances the privacy-utility trade-off compared to several state-of-the-art DPSGD variants.

Industrial Systems-on-Chips (SoCs) often comprise hundreds of thousands to millions of nets and millions to tens of millions of connectivity edges, making empirical evaluation of hardware-Trojan (HT) detectors on realistic designs both necessary and difficult. Public benchmarks remain significantly smaller and hand-crafted, while releasing truly malicious RTL raises ethical and operational risks. This work presents an automated and scalable methodology for generating HT-like patterns in industry-scale netlists whose purpose is to stress-test detection tools without altering user-visible functionality. The pipeline (i) parses large gate-level designs into connectivity graphs, (ii) explores rare regions using SCOAP testability metrics, and (iii) applies parameterized, function-preserving graph transformations to synthesize trigger-payload pairs that mimic the statistical footprint of stealthy HTs. When evaluated on the benchmarks generated in this work, representative state-of-the-art graph-learning models fail to detect Trojans. The framework closes the evaluation gap between academic circuits and modern SoCs by providing reproducible challenge instances that advance security research without sharing step-by-step attack instructions.

As machine learning systems move from theory to practice, they are increasingly tasked with decisions that affect healthcare access, financial opportunities, hiring, and public services. In these contexts, accuracy is only one piece of the puzzle - models must also be fair to different groups, protect individual privacy, and remain accountable to stakeholders. Achieving all three is difficult: differential privacy can unintentionally worsen disparities, fairness interventions often rely on sensitive data that privacy restricts, and automated pipelines ignore that fairness is ultimately a human and contextual judgment. We introduce FAIRPLAI (Fair and Private Learning with Active Human Influence), a practical framework that integrates human oversight into the design and deployment of machine learning systems. FAIRPLAI works in three ways: (1) it constructs privacy-fairness frontiers that make trade-offs between accuracy, privacy guarantees, and group outcomes transparent; (2) it enables interactive stakeholder input, allowing decision-makers to select fairness criteria and operating points that reflect their domain needs; and (3) it embeds a differentially private auditing loop, giving humans the ability to review explanations and edge cases without compromising individual data security. Applied to benchmark datasets, FAIRPLAI consistently preserves strong privacy protections while reducing fairness disparities relative to automated baselines. More importantly, it provides a straightforward, interpretable process for practitioners to manage competing demands of accuracy, privacy, and fairness in socially impactful applications. By embedding human judgment where it matters most, FAIRPLAI offers a pathway to machine learning systems that are effective, responsible, and trustworthy in practice. GitHub: https://github.com/Li1Davey/Fairplai

The integration of Artificial Intelligence (AI) in Network Intrusion Detection Systems (NIDS) is a promising approach to tackle the increasing sophistication of cyberattacks. However, since Machine Learning (ML) and Deep Learning (DL) models rely heavily on the quality of their training data, the lack of diverse and up-to-date datasets hinders their generalization capability to detect malicious activity in previously unseen network traffic. This study presents an experimental validation of the reliability of the GeNIS dataset for AI-based NIDS, to serve as a baseline for future benchmarks. Five feature selection methods, Information Gain, Chi-Squared Test, Recursive Feature Elimination, Mean Absolute Deviation, and Dispersion Ratio, were combined to identify the most relevant features of GeNIS and reduce its dimensionality, enabling a more computationally efficient detection. Three decision tree ensembles and two deep neural networks were trained for both binary and multiclass classification tasks. All models reached high accuracy and F1-scores, and the ML ensembles achieved slightly better generalization while remaining more efficient than DL models. Overall, the obtained results indicate that the GeNIS dataset supports intelligent intrusion detection and cyberattack classification with time-based and quantity-based behavioral features.

With increasingly sophisticated cybersecurity threats and rising demand for network automation, autonomous cybersecurity mechanisms are becoming critical for securing modern networks. The rapid expansion of Internet of Things (IoT) systems amplifies these challenges, as resource-constrained IoT devices demand scalable and efficient security solutions. In this work, an innovative Intrusion Detection System (IDS) utilizing Automated Machine Learning (AutoML) and Multi-Objective Optimization (MOO) is proposed for autonomous and optimized cyber-attack detection in modern networking environments. The proposed IDS framework integrates two primary innovative techniques: Optimized Importance and Percentage-based Automated Feature Selection (OIP-AutoFS) and Optimized Performance, Confidence, and Efficiency-based Combined Algorithm Selection and Hyperparameter Optimization (OPCE-CASH). These components optimize feature selection and model learning processes to strike a balance between intrusion detection effectiveness and computational efficiency. This work presents the first IDS framework that integrates all four AutoML stages and employs multi-objective optimization to jointly optimize detection effectiveness, efficiency, and confidence for deployment in resource-constrained systems. Experimental evaluations over two benchmark cybersecurity datasets demonstrate that the proposed MOO-AutoML IDS outperforms state-of-the-art IDSs, establishing a new benchmark for autonomous, efficient, and optimized security for networks. Designed to support IoT and edge environments with resource constraints, the proposed framework is applicable to a variety of autonomous cybersecurity applications across diverse networked environments.

Static analysis tools provide a powerful means to detect security vulnerabilities by specifying queries that encode vulnerable code patterns. However, writing such queries is challenging and requires diverse expertise in security and program analysis. To address this challenge, we present QLCoder - an agentic framework that automatically synthesizes queries in CodeQL, a powerful static analysis engine, directly from a given CVE metadata. QLCode embeds an LLM in a synthesis loop with execution feedback, while constraining its reasoning using a custom MCP interface that allows structured interaction with a Language Server Protocol (for syntax guidance) and a RAG database (for semantic retrieval of queries and documentation). This approach allows QLCoder to generate syntactically and semantically valid security queries. We evaluate QLCode on 176 existing CVEs across 111 Java projects. Building upon the Claude Code agent framework, QLCoder synthesizes correct queries that detect the CVE in the vulnerable but not in the patched versions for 53.4% of CVEs. In comparison, using only Claude Code synthesizes 10% correct queries. QLCoder code is available publicly at https://github.com/neuralprogram/QLCoder.

Hardware-software leakage contracts have emerged as a formalism for specifying side-channel security guarantees of modern processors, yet verifying that a complex hardware design complies with its contract remains a major challenge. While verification provides strong guarantees, current verification approaches struggle to scale to industrial-sized designs. Conversely, prevalent hardware fuzzing approaches are designed to find functional correctness bugs, but are blind to information leaks like Spectre. To bridge this gap, we introduce a novel and scalable approach: coverage-guided hardware-software contract fuzzing. Our methodology leverages a self-compositional framework to make information leakage directly observable as microarchitectural state divergence. The core of our contribution is a new, security-oriented coverage metric, Self-Composition Deviation (SCD), which guides the fuzzer to explore execution paths that violate the leakage contract. We implemented this approach and performed an extensive evaluation on two open-source RISC-V cores: the in-order Rocket Core and the complex out-of-order BOOM core. Our results demonstrate that coverage-guided strategies outperform unguided fuzzing and that increased microarchitectural coverage leads to a faster discovery of security vulnerabilities in the BOOM core.

Recent technologies such as inter-ledger payments, non-fungible tokens, and smart contracts are all fruited from the ongoing development of Distributed Ledger Technologies. The foreseen trend is that they will play an increasingly visible role in daily life, which will have to be backed by appropriate operational resources. For example, due to increasing demand, smart contracts could soon face a shortage of knowledgeable users and tools to handle them in practice. Widespread smart contract adoption is currently limited by security, usability and costs aspects. Because of a steep learning curve, the handling of smart contracts is currently performed by specialised developers mainly, and most of the research effort is focusing on smart contract security, while other aspects like usability being somewhat neglected. Specific tools would lower the entry barrier, enabling interested non-experts to create smart contracts. In this paper we designed, developed and tested Blockly2Hooks, a solution towards filling this gap even in challenging scenarios such as when the smart contracts are written in an advanced language like C. With the XRP Ledger as a concrete working case, Blockly2Hooks helps interested non-experts from the community to learn smart contracts easily and adopt the technology, through leveraging well-proven teaching methodologies like Visual Programming Languages, and more specifically, the Blockly Visual Programming library from Google. The platform was developed and tested and the results are promising to make learning smart contract development smoother.

Large Vision-Language Models (VLMs) are susceptible to jailbreak attacks: researchers have developed various attack strategies that bypass the safety mechanisms of VLMs. Among these approaches, jailbreak methods based on the Out-of-Distribution (OOD) strategy have garnered widespread attention due to their simplicity and effectiveness. This paper further advances the understanding of OOD-based VLM jailbreak methods. We show that mild OOD manipulations can achieve stronger jailbreak performance than both clean inputs and overly strong perturbations, a non-monotonic pattern we define as "weak-OOD". We explain this phenomenon through a trade-off between two dominant factors: input intent perception and model refusal triggering. Our evidence suggests that these two factors respond differently to OOD manipulations, which is consistent with a discrepancy between broad pre-training robustness and narrower safety alignment. Building on this insight, we draw inspiration from optical character recognition (OCR) capability enhancement—a core task in the pre-training phase of mainstream VLMs. Leveraging this capability, we design JOCR (Jailbreak via OCR-Aware Embedded Text Perturbation), a practical OCR-readable extension of embedded-text jailbreaks that achieves the best average ASR among evaluated baselines. Code is available at GitHub: https://github.com/Yuxuan2003/weak-ood-jailbreak.

As cyber threats continue to evolve in complexity and frequency, robust endpoint protection is essential for organizational security. This paper presents "Endpoint Security Agent: A Comprehensive Approach to Real-time System Monitoring and Threat Detection" a modular, real-time security solution for Windows endpoints. The agent leverages native tools like WMI and ETW for lowlevel monitoring of system activities such as process execution, registry modifications, and network behaviour. A machine learning-based detection engine, trained on labelled datasets of benign and malicious activity, enables accurate threat identification with minimal false positives. Detection techniques are mapped to the MITRE ATT&CK framework for standardized threat classification. Designed for extensibility, the system includes a centralized interface for alerting and forensic analysis. Preliminary evaluation shows promising results in detecting diverse attack vectors with high accuracy and efficiency.

To ensure that Machine Learning (ML) models can perform a robust detection and classification of cyberattacks, it is essential to train them with high-quality datasets with relevant features. However, it can be difficult to accurately represent the complex traffic patterns of an attack, especially in Internet-of-Things (IoT) networks. This paper studies the impact that seemingly similar features created by different network traffic flow exporters can have on the generalization and robustness of ML models. In addition to the original CSV files of the Bot-IoT, IoT-23, and CICIoT23 datasets, the raw network packets of their PCAP files were analysed with the HERA tool, generating new labelled flows and extracting consistent features for new CSV versions. To assess the usefulness of these new flows for intrusion detection, they were compared with the original versions and were used to fine-tune multiple models. Overall, the results indicate that directly analysing and preprocessing PCAP files, instead of just using the commonly available CSV files, enables the computation of more relevant features to train bagging and gradient boosting decision tree ensembles. It is important to continue improving feature extraction and feature selection processes to make different datasets more compatible and enable a trustworthy evaluation and comparison of the ML models used in cybersecurity solutions.

Modern encryption algorithms form the foundation of digital security. However, the widespread use of encryption algorithms results in significant challenges for network defenders in identifying which specific algorithms are being employed. More importantly, we find that when the plaintext distribution of test data departs from the training data, the performance of classifiers often declines significantly. This issue exposes the feature extractor's hidden dependency on plaintext features. To reduce this dependency, we adopt a method that does not learn end-to-end from ciphertext bytes. Specifically, this method is based on a set of statistical tests to compute the randomness feature of the ciphertext, and then uses the frequency distribution pattern of this feature to construct the algorithms' respective fingerprints. The experimental results demonstrate that our method achieves high discriminative performance (e.g., AUC > 0.98) in the Canterbury Corpus dataset, which contains a diverse set of data types. Furthermore, in our cross-domain evaluation, baseline models' performance degrades significantly when tested on data with a reduced proportion of structured plaintext. In sharp contrast, our method demonstrates high robustness: performance degradation is minimal when transferring between different structured domains, and even on the most challenging purely random dataset, it maintains a high level of ranking ability (AUC > 0.90).

Threat modeling has long guided software development work, and we consider how Public Threat Models (PTM) can convey useful security information to others. We list some early adopter precedents, explain the many benefits, address potential objections, and cite regulatory drivers. Internal threat models may not be directly suitable for disclosure so we provide guidance for redaction and review, as well as when to update models (published or not). In a concluding call to action, we encourage the technology community to openly share their PTMs so the security properties of each component are known up and down the supply chain. Technology providers proud of their security efforts can show their work for competitive advantage, and customers can ask for and evaluate PTMs rather than be told "it's secure" but little more. Many great products already have fine threat models, and turning those into PTMs is a relatively minor task, so we argue this should (and easily could) become the new norm.