This research tackles challenges in traditional fuzzing, such as limited coverage, instability, and inefficiency in bug discovery. We propose two novel models and their combination to enhance mutation processes and improve its reliability through unbiased randomisation, building on cryptographic techniques from our prior work. To our knowledge, we are the first to apply this approach to AFL++ , extending Feistel-inspired mutation and high-performance randomisation to generate high-quality test cases, with potential to attract attention in the fuzzing community. • Integrate and assess Feistel-inspired mutations’ impact on AFL++ performance, focusing on code coverage and stability. • Integrate the Permuted Congruential Generator ( PCG ) into AFL++ and evaluate its performance compared to traditional random number generators ( RNGs ). • Evaluate a hybrid model combining Feistel and PCG randomness for better stability and coverage. We enhance AFL++ with algorithmic improvements and RNGs modifications. Our models include: • CAFL++ ( Cryptographic - AFL++ ): Integrates Feistel-inspired transformations for improved coverage. • PCGAFL++ : Refines the AFL ’s RNG with PCG to reduce bias. • CPCGAFL++ : Combines Feistel-inspired swaps and PCG -based RNG for a robust fuzzing approach. Performance was analysed using metrics like Code Coverage and the Vargha-Delaney_A12 statistic across 20 Fuzzbench targets, and bug discovery on three targets. Our models showed significant improvements over AFL++ . CAFL++ outperformed AFL++ in 75% of test targets, offering better code coverage and stability. PCGAFL++ surpassed AFL++ in 60% of targets by enhancing randomness, resulting in more efficient fuzzing. CPCGAFL++ demonstrated improved stability and enhanced bug discovery performance, while achieving code coverage comparable to AFL++ . These results highlight the key improvements introduced by our two models for fuzz testing. Our models advance fuzzing by improving code coverage and stability. Integrating Feistel-inspired swaps and PCG -based RNG overcomes traditional fuzzing limitations, offering a more efficient and reliable method. These models represent a step forward in fuzzing techniques, influencing both academic research and industrial practices.

This paper presents the applicability of a mycelium-inspired reservoir network through an innovative extension of the Memristive Oscillating Cellular Automata (MOCA) circuit-based network. Drawing on the adaptive, self-organizing properties of mycelium, this MOCA grid employs SiNx-based RRAMs to form reconfigurable, dynamic connections that replicate mycelial network behaviors. Using the Stanford-PKU RRAM model, the non-linear properties of the fabricated devices have been characterized, establishing a flexible reservoir network capable of transforming and encoding input signals. The network has been evaluated, demonstrating small-world characteristics, including high clustering and short average path lengths, critical for effective information propagation and complex local dynamics. The resulting adaptable circuit offers a scalable foundation for future applications in bioinspired reservoir computing.

Mycelium, the vegetative structure of fungi, exhibits complex electrical signaling patterns when stimulated that resemble neural-like activity, which can be leveraged for bio-inspired computing and sensing applications. To replicate this activity, a 100x100 grid-based circuit has been designed capable of spiking behavior and adaptable configuration thanks to memristive technology aligned with fabricated devices, mimicking the dynamics seen in mycelial networks. Simulations have been carried out to demonstrate that the memristive grid successfully replicates key aspects of mycelium’s electrical activity recorded from experimental setups, including response to environmental stimuli, spiking signal propagation, and eradication.

ABSTRACT The characteristics of soft robots make them better candidates for applications such as healthcare, due to their enhanced safety, adaptability, and more natural human‐robot interaction compared to traditional counterparts. Different actuating systems have been proposed for soft robotics. On the other hand, since this technology is fairly young, the design process of soft actuators is not yet well formalized. In an attempt to enhance the applicability of this type of actuator, the utilization of a NeuroEvolution algorithm to automatically design them is proposed here. More specifically, Hypercube‐based NeuroEvolution of Augmented Topologies (HyperNEAT) is investigated for different substrate architectures. These substrates are Artificial Neural Networks that encode the three‐dimensional representation of the soft actuators. The produced three‐dimensional sketches are tested within a simulated environment under two different targets (the maximum displacement and the combination of maximum displacement and minimum actuator volume) to identify the suitability of HyperNEAT as an efficient designing methodology. Since the evaluation of candidate solutions under a physics simulator is the most computationally demanding process, the proposed methodology was realized under a client‐server setting, with the aim of accelerating the evolutionary optimization of actuator sketches. The evaluation part of the algorithm was outsourced to the server side, which can be a specialized and high‐performing computational entity. The resulting soft actuators of this study proved to be of higher competence when compared with actuators derived under previously published evolutionary methodologies.

Abstract Mycelium, the intricate vegetative network of fungi, has emerged as a promising candidate within the realm of engineered living materials (ELMs). While its intriguing structural and electrical properties highlight its potential, mycelium growth is highly sensitive to environmental conditions. To bridge this gap, a robust framework was developed to both model mycelium growth and explore its computational capabilities. This framework uses a cellular automata (CA) approach, enhanced with reaction-diffusion (RD) processes, to simulate mycelium growth under diverse environmental conditions. This configuration, combined with tunable parameters, enables the identification and validation of optimal growth patterns, supported by an algorithm designed to extract key features of hyphae–the fundamental building blocks of the mycelial network. Subsequently, the small-world properties of the modeled mycelium networks were investigated, revealing high clustering coefficients and short path lengths, characteristics that make them well-suited for reservoir computing (RC). To demonstrate their computational capabilities, mycelium-inspired RC architectures were evaluated on the MNIST dataset classification task, achieving an accuracy of up to 97.09%, highlighting the effectiveness of biologically inspired models. As a result, this framework establishes a comprehensive test-bench for mycelium modeling, growth, and computational exploration, paving the way for innovative applications in bio-inspired computing.

In medical-related tasks, soft robots can perform better than conventional robots because of their compliant building materials and the movements they are able perform. However, designing soft robot controllers is not an easy task, due to the non-linear properties of their materials. A formal design process is needed since human expertise to design such controllers is not sufficiently effective. The present research proposes neuroevolution-based algorithms as the core mechanism to automatically generate controllers for biohybrid actuators that can be used on future medical devices, such as a catheter that will deliver drugs. The controllers generated by methodologies based on Neuroevolution of Augmenting Topologies (NEAT) and Hypercube-based NEAT (HyperNEAT) are compared against the ones generated by a standard genetic algorithm (SGA). In specific, the metrics considered are the maximum displacement in upward bending movement and the robustness to control different biohybrid actuator morphologies without redesigning the control strategy. Results indicate that the neuroevolution-based algorithms produce better-suited controllers than the SGA. In particular, NEAT designed the best controllers, achieving up to 25% higher displacement when compared with SGA-produced specialised controllers trained over a single morphology and 23% when compared with general-purpose controllers trained over a set of morphologies.

Modern software and networks underpin our digital society, yet the rapid growth of vulnerabilities that are uncovered within these threaten our cyber security posture. Addressing these issues at scale requires automated proactive approaches that can identify and mitigate these vulnerabilities in a suitable time frame. Fuzzing techniques have emerged as crucial methods to preemptively tackle these risks. However, traditional fuzzing methods encounter various challenges, such as a lack of strategy for deep bug identification, time-intensive bug analysis, quality of inputs, seed scheduling and others. To overcome these challenges, diverse Machine Learning (ML) models and optimisation techniques have been employed, including advanced feature engineering, optimised seed selection, refined predictive/fitness models, and Gradient-based optimisation. Furthermore, the use of ML architectures such as Long Short-Term Memory (LSTM), Generative Adversarial Network (GAN), Sequence-to-Sequence (Seq2Seq), and Generative Randomised Unit (GRU), have demonstrated greater effectiveness within ML-based fuzzing. In this paper, we delve into this paradigm shift, aiming to address fundamental challenges across different ML categories. We survey popular ML categories such as Traditional Machine Learning (TML), Deep Learning (DL), Reinforcement Learning (RL), and Deep Reinforcement Learning (DRL), to investigate their potential for enhancing traditional fuzzing approaches. We explore the respective advantages in each category of ML-based fuzzing, while also analysing the challenges unique to each category. Our work provides a comprehensive survey across the fuzzing domain and how machine learning techniques have been utilised, that we believe will be of use to future researchers in this domain.

There is a continuous urge for higher efficiency in conventional computing systems, driven by an ever-growing demand for these systems’ complexity to be able to match the one of convoluted and challenging problems. However, this type of problems has formulated the benchmarks for unconventional computing systems to validate their emerging applicability and prove their effectiveness. Towards this path, Cellular Automata (CAs) have been established as a promising mathematical tool for simulating physical processes and demonstrated a favourable methodology for effectively implementing computations in hardware by taking advantage of their inherent parallelism. Representing CAs with oscillating memristive networks could further enhance the performance of these systems, by incorporating the rich dynamics evident in memristors and their strong memory and computing features. In this work, a wave generator circuit has been designed with low-voltage fabricated CBRAM devices, that is able to act as a Wave Cellular Automaton (WCA). These wave generation units are located on a grid with adjusting multi-directional interconnections between neighbors. In addition to that, the ability to reconFigure the amount of such units that influence each other, facilitates the propagation of voltage signals through the grid following wave propagation features. An example of this computational domain is presented with the realization of complex logic gates on the grid of WCAs.

The threshold switching effect is critical in memristor devices for a range of applications, from crossbar design reliability to simulating neuromorphic features using artificial neural networks. The rich inherit dynamics of a metallic conductive filament (CF) formation are thought to be linked to this characteristic. Simulating these dynamics is necessary to develop an accurate memristor model. In this work we present a compact memristor model that utilizes the drift, diffusion and thermo-diffusion effects. These three effects are taken into consideration to derive the switching behavior of a memristor. The resistance of a memristor is calculated based on the evolution of a truncated cone shaped filament. The objective of this model is to achieve a realistic integration of switching mechanisms of the memristor device, while minimizing the overhead on computing resources and being compatible with circuit design tools. The model incorporates the effect of thermo-diffusion on the switching pattern, providing a different perception of the ionic transport processes, which enable the unipolar switching. SPICE simulation results provide an exact match with experimental results of Metal-Insulator-Metal (MIM) memristive devices of Ag/Si2/SiO2.07/Pt nanoparticles (NPs) configuration.

Synchronization transition in neuromorphic networks has attracted much attention recently as a fundamental property of biological neural networks, which relies on network connectivity along with different synaptic features. In this work, an area-optimized FPGA implementation of an Asynchronous Cellular Automata Neuron model that exhibits discrete-state neuron dynamics is introduced. The proposed neuron model is capable of reproducing various neuromorphic oscillations observed in biological neurons using less hardware resources than previous implementations. We investigate synchronization transitions with a focus on the emergence of chimera states in a ring-based network consisting of hardware-based neurons with electrical synaptic coupling. In particular, we study the effects on the network’s phase synchronization through changing two control parameters: the coupling range and the coupling strength. We indicate that via proper configuration of the coupling parameters, we influence the synchronization transition and reveal chimera states which have been associated with neurological disorders.

An accurate modelling of bio-electrochemical processes that govern Microbial Fuel Cells (MFCs) and mapping their behavior according to several parameters will enhance the development of MFC technology and enable their successful implementation in well defined applications. The geometry of the electrodes is among key parameters determining efficiency of MFCs due to the formation of a biofilm of anodophilic bacteria on the anode electrode, which is a decisive factor for the functionality of the device. We simulate the bio-electrochemical processes in an MFC while taking into account the geometry of the electrodes. Namely, lattice Boltzmann methods are used to simulate the fluid dynamics and the advection-diffusion phenomena in the anode compartment. The model is verified on voltage and current outputs of a single MFC derived from laboratory experiments under continuous flow. Conclusions can be obtained from a parametric analysis of the model concerning the design of the geometry of the anode compartment, the positioning and microstructure of the anode electrode, in order to achieve more efficient overall performance of the system. An example of such a parametric analysis is presented here, taking into account the positioning of the electrode in the anode compartment.

Man-made transport networks and their design are closely related to the shortest path problem and considered amongst the most debated problems of computational intelligence. Apart from using conventional or bio-inspired computer algorithms, many researchers tried to solve this kind of problem using biological computing substrates, gas-discharge solvers, prototypes of a mobile droplet, and hot ice computers. In this aspect, another example of biological computer is the plasmodium of acellular slime mould Physarum polycephalum (P. polycephalum), which is a large single cell visible by an unaided eye and has been proven as a reliable living substrate for implementing biological computing devices for computational geometry, graph-theoretical problems, and optimization and imitation of transport networks. Although P. polycephalum is easy to experiment with, computing devices built with the living slime mould are extremely slow; it takes slime mould days to execute a computation. Consequently, mapping key computing mechanisms of the slime mould onto silicon would allow us to produce efficient bio-inspired computing devices to tackle with hard to solve computational intelligence problems like the aforementioned. Toward this direction, a cellular automaton (CA)-based, Physarum-inspired, network designing model is proposed. This novel CA-based model is inspired by the propagating strategy, the formation of tubular networks, and the computing abilities of the plasmodium of P. polycephalum. The results delivered by the CA model demonstrate a good match with several previously published results of experimental laboratory studies on imitation of man-made transport networks with P. polycephalum. Consequently, the proposed CA model can be used as a virtual, easy-to-access, and biomimicking laboratory emulator that will economize large time periods needed for biological experiments while producing networks almost identical to the tubular networks of the real-slime mould.