The first pillar of the framework is the abstract syntax tree, or AST. Every program, whether benign or malicious, is written in a programming language with strict grammatical rules, and a compiler can represent that structure as a tree in which each node corresponds to a syntactic construct: a loop, a function call, a conditional branch, a memory operation. This representation is powerful for security because it is relatively insensitive to superficial changes. Renaming variables, reordering harmless statements, or inserting dead code alters the raw byte sequence of a binary dramatically, but the essential shape of the syntax tree often survives such transformations. By modeling the syntactic and semantic structure of code through ASTs, the framework captures what a program actually does rather than what its bytes happen to look like, which is precisely the property needed to unmask polymorphic malware families that continuously rewrite their own appearance.

Structure alone, however, does not tell the whole story, and this is where the second pillar comes in. The researchers complement the AST representation with L-moments, a family of statistical descriptors that summarize the distribution of features extracted from the code. L-moments are linear combinations of order statistics, and unlike classical moments such as the mean and variance, they remain stable even when the data contain outliers or heavy-tailed noise. In a security context this robustness matters enormously. Malware samples are frequently packed, encrypted, or partially corrupted, and the features derived from them can be noisy in ways that would distort conventional statistical summaries. Because L-moments are resilient to noise and outliers, they provide a stable statistical signature of a sample that persists even when adversaries deliberately perturb the code to confuse a classifier. The combination of a structural view from the AST and a statistical view from the L-moments gives the system two independent lenses on the same suspicious file.

The third pillar extends the analysis into relational territory. The framework constructs multi-dimensional graph representations of each sample, in which nodes correspond to code elements and edges encode the dependencies and interactions among them. Graph analysis then uncovers hidden dependencies that neither the tree nor the statistics can reveal on their own. The study draws on well-established graph-theoretic measures, including degree centrality, closeness centrality, and betweenness centrality, each of which characterizes a different aspect of how information flows through the code. A node with high betweenness centrality, for example, sits on many shortest paths between other nodes and may represent a critical dispatch function that malicious logic funnels through. By examining these relational patterns, the system can identify subtle malicious behaviors, such as covert communication channels or obfuscated control flow, that manifest as unusual graph structures rather than as any single suspicious instruction.

Feeding these three complementary representations into a classifier is where the framework earns the word hybrid in its name. At the heart of the classification stage sits a Quantum-Inspired Neural Network, or QINN, a class of models that borrows mathematical machinery from quantum physics without requiring quantum hardware. The framework also incorporates concepts from the Quantum Boltzmann Machine, a generative model built around a Hamiltonian energy function, a partition function, and an inverse temperature parameter that governs how the model trades off exploration against convergence. Quantum-inspired approaches of this kind have attracted growing attention in cybersecurity research because their underlying mathematics can capture complex, high-dimensional probability distributions more expressively than some classical architectures. In this framework, the QINN serves as the engine that fuses structural, statistical, and relational features into a single decision about whether a sample is malicious and, if so, what family it belongs to.

Adaptability is the framework’s answer to the relentless evolution of threats. The authors integrate self-supervised learning, which allows the model to learn useful representations from unlabeled samples before any expensive labeling takes place, and meta-learning, sometimes described as learning to learn. Meta-learning trains the classifier in a way that prepares it to generalize rapidly to previously unseen malware families from only a handful of labeled examples, a scenario that mirrors the real world, where brand-new threats appear daily and labeled data lag far behind. Transfer learning further accelerates this process by carrying knowledge from well-studied malware families over to emerging ones. Together, these techniques aim to solve one of the most persistent pain points in applied machine learning for security: the cold-start problem, in which a model trained on yesterday’s threats fails embarrassingly on today’s.

The framework does not stop at static adaptation. A reinforcement learning mechanism enables real-time model updates, allowing the system to keep learning as new samples stream in from the wild. In this scheme, the classifier’s decisions are treated as actions, and feedback signals drive a reward process that adjusts the model’s parameters over time, with a discount factor balancing immediate accuracy against long-term performance. This continuous learning loop is designed for dynamic cybersecurity environments, where the distribution of threats shifts from one week to the next and a frozen model silently degrades. By combining meta-learning for rapid generalization with reinforcement learning for ongoing refinement, the researchers describe a system intended to remain effective not just at the moment of deployment but across the entire lifetime of a security operation.

The experimental evaluation was conducted on a large-scale, publicly available real-world dataset drawn from MalwareBazaar, a widely used repository of live malware samples, rather than on curated academic benchmarks that often overstate real-world performance. Against this demanding testbed, the framework achieved an accuracy of 98.62 percent, a precision of 96.14 percent, a recall of 95.28 percent, and an F1-score of 95.71 percent, surpassing traditional machine learning baselines such as support vector machines as well as deep learning approaches including convolutional and recurrent architectures. Precision and recall together matter in security practice: high precision limits the false alarms that exhaust analyst attention, while high recall limits the dangerous misses that let infections through. The balanced F1-score of 95.71 percent suggests the system manages both sides of that trade-off simultaneously rather than sacrificing one for the other.

Perhaps the most consequential claim in the study concerns robustness against adversarial attacks and evasion techniques. Modern attackers increasingly target the machine learning models inside defenses themselves, crafting inputs that are minimally altered yet cause catastrophic misclassification. Because the proposed framework anchors its decisions in structural syntax, noise-resistant statistics, and relational graph patterns rather than in fragile byte-level signatures, it presents a much harder moving target for such evasion. The authors report that the system exhibited strong robustness under adversarial conditions, a property that builds on a growing body of work exploring quantum-inspired defenses for machine learning models in cybersecurity. If this resilience holds up under independent scrutiny, it would address one of the most troubling weaknesses of AI-based malware detection as currently deployed.

The research, carried out by teams at Galgotias University and Bennett University in India, Texas A&M University-Kingsville in the United States, and Princess Nourah bint Abdulrahman University in Saudi Arabia, arrives amid a broader wave of graph-based and quantum-inspired approaches to threat detection, from graph convolutional networks for Android malware to quantum-enhanced classifiers for malicious URL detection. What distinguishes this work is the deliberate fusion of multiple complementary views of a single sample into one adaptive pipeline. No single representation, the authors argue, is sufficient against adversaries who can mutate every surface feature of their code; only a framework that reads malware simultaneously as syntax, as statistics, and as a network of relationships can generalize reliably. As cyber threats continue to evolve at machine speed, defenses that can learn, adapt, and resist manipulation in kind may define the next generation of cybersecurity, and this study offers a concrete, quantitatively validated blueprint for what such a defense could look like.

Subject of Research: A hybrid machine learning framework for malware detection and classification using abstract syntax trees, L-moments, graph analysis, and quantum-inspired neural networks

Article Title: A hybrid framework for malware detection leveraging abstract syntax trees, L-moments, and multi-dimensional graphs with quantum-inspired neural networks

Article References: A hybrid framework for malware detection leveraging abstract syntax trees, L-moments, and multi-dimensional graphs with quantum-inspired neural networks. (n.d.). https://doi.org/10.1007/s10586-026-06579-8

Image Credits: AI Generated

DOI: 10.1007/s10586-026-06579-8

Keywords: malware detection, quantum-inspired neural networks, abstract syntax trees, L-moments, graph analysis, machine learning, meta-learning, self-supervised learning, reinforcement learning, adversarial robustness, cybersecurity, Cluster Computing

The scale of the malware problem provides the backdrop for this work. According to the Symantec Internet Security Threat Report cited by the authors, more than 430 million new malware samples have been discovered, with an average of 1.2 million malware attacks launched every day. Traditional detection methods, which often depend on matching known signatures, struggle against new, unknown, or deliberately obfuscated attacks. As attackers grow more sophisticated, defenders need techniques that can spot malicious behavior even when the code has never been seen before or is designed to lie dormant until it is safe to strike.

Dynamic Malware Analysis, or DMA, offers one promising answer. Rather than examining a program’s static code, DMA runs the suspicious program inside a controlled environment and watches what it actually does: how it alters memory spaces, injects processes, makes unusual system or API calls, modifies the registry, and interacts with the network. Because it observes behavior rather than appearance, DMA can catch malware that evades signature-based tools, including obfuscated variants and fileless threats that hide in memory. The system memory data collected during execution is then handed to a machine learning classifier, which decides whether the activity looks malicious or benign.

But DMA carries a heavy computational burden. Memory dumps are enormous, and the features extracted from them frequently include redundant or irrelevant information that inflates processing time, consumes resources, and can even degrade classification accuracy. This is where feature selection comes in. By identifying the most informative subset of features, feature selection reduces dimensionality, lowers computational cost, and reduces the risk of overfitting, in which a model memorizes noise in the training data instead of learning the underlying patterns that generalize to new samples. Metaheuristic optimization algorithms have proven particularly effective at navigating the vast combinatorial space of possible feature subsets.

The Harris Hawks Optimizer, first introduced as a metaheuristic for solving optimization problems, models candidate solutions as hawks searching for prey, where the prey represents the optimal solution. The algorithm alternates between exploration, in which hawks perch randomly or position themselves relative to the best solution found so far, and exploitation, in which they converge on promising regions using strategies such as soft siege, hard siege, and progressive rapid dives modeled by Levy flight mathematics. A key transition parameter, the prey’s escaping energy, decreases over iterations and governs when the search shifts from broad exploration to focused refinement. While HHO has already been applied successfully to high-dimensional DMA data, the authors note it can suffer from premature convergence, settling on suboptimal feature subsets without adequately exploring the search space.

The team’s enhancement addresses this weakness with two structural modifications. First, they replaced the standard random initialization with a hybrid scheme: half of the initial hawk population is generated using Latin Hypercube Sampling, a statistical technique that divides the solution space into segments and samples from each, ensuring a more uniform spread of starting points and faster convergence toward the global optimum. Second, they integrated a Gaussian crossover mechanism borrowed from evolutionary computation. After each iteration, pairs of hawks are blended using Gaussian distributions to produce offspring that inherit traits from both parents, and the two fittest hawks are also crossed to generate elite offspring. The population is then trimmed back to its original size by keeping only the best individuals, balancing diversity with convergence.

The experimental pipeline began with the CIC-MalMem-2022 dataset, created at the Canadian Institute for Cybersecurity. It contains 58,596 memory dump records, evenly split between benign and malicious samples, described by 55 features extracted with the VolMemLyzer-V2 analyzer from VirtualBox memory snapshots. These features capture injected code, file access, registry activity, process behavior, and redirected API calls. The researchers label-encoded the class column, applied Min-Max normalization to forty features whose raw values ranged up to 1.05 million, and then ran their improved HHO with a population of 26 hawks over 260 iterations, using a fitness function weighted toward accuracy with a small penalty for the number of selected features.

The results were striking. The improved optimizer distilled 55 features down to just four: the number of threads, the number of timers, the number of services detected in memory, and the number of callbacks, a 92.7 percent reduction in dimensionality. Among these, the service count feature showed the highest permutation importance at 0.35. The best feature subset was found roughly 40 iterations into the search. When the reduced feature set was fed to six supervised classifiers, Extra Trees achieved perfect 100 percent scores, Random Forest reached 99.98 percent, and Decision Trees, XGBoost, Gradient Boosted Trees, and AdaBoost followed closely behind. Compared with the original HHO, accuracy improved across the board, for example rising from 99.96 to 100 percent for Extra Trees and from 99.93 to 99.98 percent for Random Forest, while convergence times fell for every classifier, with Decision Trees dropping from 0.0312 to 0.0156 seconds.

The improvements were not statistical flukes. A paired Wilcoxon signed-rank test over 20 independent runs comparing the improved and original optimizers on Extra Trees accuracy yielded a test statistic of zero and a p-value of 1.9 times ten to the negative sixth, confirming significance at the 0.05 level, with a large effect size of 0.87. Against other published models built on the same CIC-MalMem-2022 dataset, which reported accuracies between 97.67 and 99.97 percent, the proposed framework achieved the highest reported binary classification accuracy while using a dramatically smaller feature subset. The authors also analyzed computational complexity, noting that the crossover operations add minimal overhead relative to the dominant cost of classifier training, and that the four-feature subset makes deployment far lighter than the original 55-feature space.

The study is not without acknowledged limitations. All experiments were conducted on a single dataset, evaluation used one stratified train-test split rather than cross-validation, and variations in sandbox configurations and memory acquisition environments were not explored. The authors say future work will add k-fold cross-validation, external dataset validation, and comparisons with other enhanced HHO variants. Still, the core message is compelling: by letting a flock of virtual hawks hunt through a high-dimensional feature space with smarter initialization and genetic recombination, the researchers showed that near-perfect malware detection does not require mountains of data, only the right handful of behavioral clues.

Subject of Research: Feature selection with an enhanced Harris Hawks Optimizer for dynamic malware detection using memory analysis

Article Title: Malware detection using dynamic analysis with a modified Harris Hawk optimizer

Article References: Anabousi, H. A., Abualhaj, M. M., Abu-Shareha, A., Yousif, M., Daoud, M. S., Faheem, M. R., & Soltani, H. (2026). Malware detection using dynamic analysis with a modified Harris Hawk optimizer. Discover Artificial Intelligence, 6(1), Article 1309. https://doi.org/10.1007/s44163-026-01359-0

Image Credits: AI Generated

DOI: 10.1007/s44163-026-01359-0

Keywords: malware detection, dynamic malware analysis, Harris Hawks Optimizer, feature selection, machine learning, metaheuristics, CIC-MalMem-2022, cybersecurity, Extra Trees, memory forensics, optimization, classification

The core insight behind the Vietnamese team’s design is that federated learning’s privacy guarantees are thinner than they first appear. During each round of training, participating devices compute gradient updates, or weight changes, on their local data and send them to a coordinating server for aggregation. Research on gradient inversion attacks has demonstrated that a sufficiently determined adversary who intercepts these updates can reconstruct recognizable images and text from them, effectively reversing the learning process to expose the very data the scheme was meant to protect. Beyond eavesdropping, federated systems are also vulnerable to poisoning attacks, in which malicious clients submit corrupted updates to degrade the shared model, and to attacks on the aggregation server itself, which represents a single point of failure and a tempting target for anyone seeking to manipulate the final model.

Homomorphic encryption addresses the eavesdropping problem with a mathematical trick that sounds almost paradoxical: it allows arithmetic to be performed directly on encrypted values. In a conventional encrypted system, data must be decrypted before anything useful can be done with it, which means the party doing the computation inevitably sees the plaintext. Homomorphic schemes, by contrast, operate on ciphertexts, producing encrypted results that, when finally decrypted by the key holder, match the outcome of the same operations performed on the underlying data. For federated learning this is a natural fit, because model aggregation is essentially weighted arithmetic, adding and averaging the numerical updates contributed by many clients. If each client encrypts its update before transmission, the server can combine them into a new global model without ever seeing a single plaintext gradient.

Not all homomorphic encryption is created equal, and the choice of scheme has enormous consequences for performance. The researchers evaluated their system under three experimental conditions: no encryption at all, Paillier encryption, and Cheon-Kim-Kim-Song, or CKKS, encryption. Paillier is a classical partially homomorphic scheme that supports additive operations on integers, which is sufficient for averaging model weights but imposes significant computational overhead on the large tensors that modern neural networks use. CKKS, introduced in 2017, takes a different approach, performing approximate arithmetic on real and complex numbers, which aligns far more naturally with the floating-point values that flow through a deep neural network. That alignment lets CKKS pack many values into a single ciphertext and process them in parallel, dramatically reducing the computational burden relative to schemes designed for exact integer arithmetic.

To measure how much this matters in practice, the team built their experiments around a convolutional neural network, the workhorse architecture for image and signal classification, and tested the system on three benchmark datasets chosen to span very different security scenarios. MNIST, the classic dataset of handwritten digits, and CIFAR-10, a more demanding collection of small natural images, represent standard machine learning workloads. The third dataset, CICMalDroid2020, is a collection of Android malware samples, which grounds the evaluation in a domain where privacy and security are not abstract concerns but operational requirements: hospitals, banks, and security vendors cannot share malware samples or user data freely, yet they would all benefit from a jointly trained detection model.

The headline security result is striking. Under adversarial attack, the system running without encryption suffered an attack success rate of 83.67 percent, meaning the vast majority of attempted intrusions into the training process succeeded. With CKKS encryption in place, that figure collapsed to 55.63 percent, a reduction of nearly thirty percentage points. The encryption does not make attacks impossible, but it strips attackers of the readable gradients and model parameters they rely on, forcing them to operate blind against ciphertexts whose contents reveal nothing about the data or the model state. Meanwhile, the efficiency numbers suggest the security does not come at an unacceptable price: training efficiency remained above 90 percent across all three datasets in the CKKS-based configuration, indicating that the cryptographic overhead, while real, leaves the bulk of the system’s training throughput intact.

Encryption alone, however, would leave federated learning exposed on a different front: trust in the infrastructure that stores and manages models. This is where the blockchain component of uitPriPreFL enters. A blockchain is a distributed, append-only ledger in which records are bundled into cryptographically linked blocks and validated by consensus among participants, making it computationally infeasible for any single party to silently alter history. In the proposed system, the blockchain serves as the storage and management backbone for model information, creating an auditable record of model versions and updates. Any participant can verify that the global model they are downloading corresponds to a legitimate aggregation of encrypted client contributions, and no central operator can quietly substitute a manipulated model or erase a previous version. The combination is synergistic: homomorphic encryption protects the content of the models, while the blockchain protects their provenance and integrity.

The broader context makes this work part of a fast-moving research wave. Recent years have seen a flurry of systems combining cryptography with decentralized ledgers to harden collaborative machine learning, from blockchain-based auditable federated learning frameworks with incentive mechanisms, to multi-key homomorphic encryption schemes that prevent even the aggregation server from decrypting individual updates, to adaptive segmented CKKS approaches designed to squeeze more efficiency out of approximate homomorphic arithmetic. Surveys of client-server attacks and defenses in federated learning document a threat landscape that includes gradient inversion, membership inference, model poisoning, and Byzantine failures, and the field has increasingly converged on the view that no single defense suffices. Layered architectures, combining encryption for confidentiality, consensus mechanisms for integrity, and aggregation rules for robustness, are emerging as the practical answer.

The Vietnamese team’s contribution to that conversation is a complete, working system rather than a theoretical proposal, and they have released the source code publicly on GitHub, allowing other researchers to reproduce their experiments, probe the implementation for weaknesses, and build on the architecture. Open availability matters in this subfield because security claims are notoriously difficult to verify from papers alone, and adversarial evaluations frequently find gaps between a system’s promised and actual robustness. By publishing code alongside benchmarks spanning handwriting recognition, natural images, and malware detection, the authors have made it possible for the community to test whether the reported attack-resistance and efficiency numbers hold up under independent scrutiny.

The implications reach well beyond the laboratory. Federated learning is already deployed in keyboard prediction on smartphones, in healthcare consortia that train diagnostic models across hospitals, and in financial fraud detection networks where data-sharing agreements make centralization impossible. Every one of those deployments inherits the vulnerabilities that gradient inversion and poisoning research have exposed, and every one of them stands to benefit from encryption that lets a server aggregate without seeing and ledgers that make model history verifiable. The uitPriPreFL results, showing a drop in attack success from nearly 84 percent to under 56 percent while keeping training efficiency above 90 percent, offer a concrete data point that strong cryptographic privacy and practical machine learning performance can coexist. As approximate homomorphic encryption schemes like CKKS continue to mature and hardware acceleration improves, the tax that privacy pays on training speed is likely to shrink further, bringing fully private, auditable, collaborative AI closer to everyday infrastructure.

Subject of Research: Privacy-preserving federated learning using homomorphic encryption and blockchain

Article Title: uitPriPreFL: privacy-preserving federated learning system using homomorphic encryption and blockchain

Article References: Cam, N. T., Anh, H. H., & Long, T. K. (2026). uitPriPreFL: privacy-preserving federated learning system using homomorphic encryption and blockchain. Cluster Computing, 29(13), Article 781. https://doi.org/10.1007/s10586-026-06603-x

Image Credits: AI Generated

DOI: 10.1007/s10586-026-06603-x

Keywords: federated learning, homomorphic encryption, blockchain, CKKS, Paillier, data privacy, machine learning security, gradient inversion, deep learning, model aggregation, cryptography, malware detection