Input Generation Research Articles

Hyperfuzzing: black-box security hypertesting with a grey-box fuzzer

Despite being a severe error where programs inadvertently reveal confidential information, insecure flows rarely receive explicit attention during software testing. LeakFuzzer uses an input-output non-interference property, specialised via a security flow policy for the program under test, to advance the state of the art. It detects insecure flows by using hypertesting for violations of the program’s non-interference property. LeakFuzzer extends the capabilities of the state of the art fuzzer, AFL++, and thus inherits its advantages such as scalability, automated input generation, high coverage and low developer intervention. It can thus detect the same set of errors as AFL++, as well as being able to detect violations of secure information flow policies at small additional performance costs. This offers a significant advance in scalability and automation for the state of the art. We evaluated LeakFuzzer on a diverse set of 12 C and C++ benchmarks containing known bugs that cause confidential information to be disclosed, ranging in size from just 80 to over 900k lines of code. Nine of these are taken from real-world CVEs including Heartbleed and a recent error in PostgreSQL. Given 20 24-hour runs, LeakFuzzer can find 100% of the insecure flows in the SUTs whereas existing techniques using the CBMC model checker and AFL++ augmented with different sanitizers can only find 40% at best.

Development of a New Thermal-Hydraulic Module for FRENETIC, a Code for the Multiphysics Analysis of Liquid Metal–Cooled Reactors

This paper describes the development of a new thermal-hydraulic (TH) module for the Fast REactor NEutronics/Thermal-hydraulICs (FRENETIC) multiphysics code for the full-core simulation of liquid metal–cooled fast reactors, developed at Politecnico di Torino. The code performs steady-state and transient neutronic (NE) and TH coupled calculations while maintaining a relatively low computational cost thanks to the adoption of simplified physical models. The NE module implements the nodal formulation of the multigroup neutron diffusion equations with delayed neutron precursors whereas the TH module treats the reactor hexagonal assemblies as separate channels, which are individually modeled as one-dimensional in the axial direction, accounting for the thermal coupling in the horizontal direction. The new TH module is more robust and portable while providing improved performance with respect to the previous implementation—also thanks to the adopted OpenMP parallelization. Some physical aspects that were previously neglected, such as the thermal inertia of nonfuel rods, have also been included in the model. The development was carried out in accordance with current best practices for code design, implementation, and testing, thus rendering the code easier to be maintained and possibly to be extended in the future. The code usability has also been improved by means of a set of Python classes purposely developed to simplify the input generation and postprocessing phases. This can potentially widen the usage of FRENETIC within the fast reactor community for the simulation of full-core coupled NE-TH transients and/or as a platform to test new solution methods. The paper also includes the application of this new FRENETIC version to a representative configuration of the Advanced Lead-cooled Fast Reactor European Demonstrator (ALFRED) core design. First, the nominal operating conditions of the ALFRED reactor were simulated, proving that the new upgrade of the code is faster and more robust with respect to the previous one. Then, two accidental transients where NE-TH feedback effects are relevant—an unprotected loss of flow and a total instantaneous blockage of a single fuel assembly—were considered.

Monte Carlo Workflow Unification for Nuclear Reactor Analysis with Metamodel-Driven Modeling

Monte Carlo (MC) transport codes are a cornerstone of nuclear reactor analysis frameworks, providing reference solutions and multigroup cross sections, and even as core components in multiphysics couplings. These applications can be seen in toolkits from the Nuclear Energy Advanced Modeling and Simulation program and the U.S. Nuclear Regulatory Commission’s BlueCRAB (Comprehensive Reactor Analysis Bundle). Contrary to their ubiquitousness in reactor physics modeling and simulation, popular MC codes, such as MCNP, Serpent, and KENO, are still reliant on antiquated textual input formats. These input languages use a plethora of keywords with terse syntax to specify all facets of a model, including its geometry, materials, physics settings, and tally options. This poses a steep learning curve and a poor user experience. Being tied to unique text-based input formats also significantly complicates programmatic input generation or modification that may be desired and/or required within a multiphysics framework. This work demonstrates how the development of programmatic interfaces for MC codes can support model unification and translation activities. Building on the Python application program interface (API) development of MCNPy, similar capabilities are being implemented for Serpent that are able to support model translation. In future work, the Serpent API capabilities will be made more robust and the work will be further expanded to include translations with KENO.

Advancing building energy modeling with large language models: Exploration and case studies

The rapid progression in artificial intelligence has facilitated the emergence of large language models like ChatGPT, offering potential applications extending into specialized engineering modeling, especially physics-based building energy modeling. This paper investigates the innovative integration of large language models with building energy modeling software, focusing specifically on the fusion of ChatGPT with EnergyPlus. A literature review is first conducted to reveal a growing trend of incorporating large language models in engineering modeling, albeit limited research on their application in building energy modeling. We underscore the potential of large language models in addressing building energy modeling challenges and outline potential applications including simulation input generation, simulation output analysis and visualization, conducting error analysis, co-simulation, simulation knowledge extraction and training, and simulation optimization. Three case studies reveal the transformative potential of large language models in automating and optimizing building energy modeling tasks, underscoring the pivotal role of artificial intelligence in advancing sustainable building practices and energy efficiency. The case studies demonstrate that selecting the right large language model techniques is essential to enhance performance and reduce engineering efforts. The findings advocate a multidisciplinary approach in future artificial intelligence research, with implications extending beyond building energy modeling to other specialized engineering modeling.

Simulation-based Flexible Needle Control with Single-core FBG Feedback for Spinal Injections.

We present a general framework of simultaneous needle shape reconstruction and control input generation for robot-assisted spinal injection procedures, without continuous imaging feedback. System input-output mapping is generated with a real-time needle-tissue interaction simulation, and single-core FBG sensor readings are used as local needle shape feedback within the same simulation framework. FBG wavelength shifts due to temperature variation is removed by exploiting redundancy in fiber arrangement. Targeting experiments performed on both plastisol lumbar phantoms as well as an ex vivo porcine lumbar section achieved in-plane tip errors of and , and total tip errors of and for the two testing environments. Our clinically inspired control strategy and workflow is self-contained and not dependent on the modality of imaging guidance. The generalizability of the proposed approach can be applied to other needle-based interventions where medical imaging cannot be reliably utilized as part of a closed-loop control system for needle guidance.

Dynamic Traffic Light Algorithm Incorporating Post-Intersection Space Allocation

This research presents a novel dynamic traffic light algorithm designed to optimize traffic flow and reduce traffic congestion by dynamically allocating green time based on post-intersection space availability. The algorithm employs a three-stage process: input generation, processing, and output. The input stage involves capturing traffic images using cameras strategically placed at intersections, which are then processed using background subtraction, edge detection, and object counting techniques. The processing phase includes vehicle counting using the YOLOv8 algorithm and open space calculation based on the maximum capacity of each road section. The output phase involves dynamically allocating green time to roads based on available post-intersection space and occupancy rates. The algorithm is designed to adapt to changing traffic conditions by continuously monitoring the post- intersection space and adjusting green times accordingly. It also incorporates a reset timer to ensure the algorithm loops back to the initial stage of gathering and processing traffic images. Simulation experiments using a physical model with toy vehicles and a camera setup demonstrated the benefits of this approach. Compared to the density-based approaches[1], this algorithm reduced average vehicle delay by 20-30%, increased overall intersection throughput by 15-25%, and decreased maximum queue lengths in each lane by 25-35%. It also adapted more effectively to fluctuations in traffic conditions, improving performance metrics by 20-30%. These results highlight the potential of incorporating downstream space considerations into traffic light control algorithms to enhance intersection efficiency, reduce traffic congestion, and enable more adaptive and fair traffic management.

Fairness Testing of Machine Translation Systems

Machine translation is integral to international communication and extensively employed in diverse human-related applications. Despite remarkable progress, fairness issues persist within current machine translation systems. In this article, we propose FairMT, an automated fairness testing approach tailored for machine translation systems. FairMT operates on the assumption that translations of semantically similar sentences, containing protected attributes from distinct demographic groups, should maintain comparable meanings. It comprises three key steps: (1) test input generation, producing inputs covering various demographic groups; (2) test oracle generation, identifying potential unfair translations based on semantic similarity measurements; and (3) regression, discerning genuine fairness issues from those caused by low-quality translation. Leveraging FairMT, we conduct an empirical study on three leading machine translation systems–Google Translate, T5, and Transformer. Our investigation uncovers up to 832, 1,984, and 2,627 unfair translations across the three systems, respectively. Intriguingly, we observe that fair translations tend to exhibit superior translation performance, challenging the conventional wisdom of a fairness-performance tradeoff prevalent in the fairness literature.

LUNAR: Automated Input Generation and Analysis for Reactive LAMMPS Simulations.

Generating simulation-ready molecular models for the LAMMPS molecular dynamics (MD) simulation software package is a difficult task and impedes the more widespread and efficient use of MD in materials design and development. Fixed-bond force fields generally require manual assignment of atom types, bonded interactions, charges, and simulation domain sizes. A new LAMMPS pre- and postprocessing toolkit (LUNAR) is presented that efficiently builds molecular systems for LAMMPS. LUNAR automatically assigns atom types, generates bonded interactions, assigns charges, and provides initial configuration methods to generate large molecular systems. LUNAR can also incorporate chemical reactivity into simulations by facilitating the use of the REACTER protocol. Additionally, LUNAR provides postprocessing for free volume calculations, cure characterization calculations, and property predictions from LAMMPS thermodynamic outputs. LUNAR has been validated via building and simulation of pure epoxy and cyanate ester polymer systems with a comparison of the corresponding predicted structures and properties to benchmark values, including experimental results from the literature. LUNAR provides the tools for the computationally driven development of next-generation composite materials in the Integrated Computational Materials Engineering (ICME) and Materials Genome Initiative (MGI) frameworks. LUNAR is written in Python with the usage of NumPy and can be used via a graphical user interface, a command line interface, or an integrated design environment. LUNAR is freely available via GitHub.

Classification of Indonesian adult forensic gender using cephalometric radiography with VGG16 and VGG19: a Preliminary research.

The use of cephalometric pictures in dental radiology is widely acknowledged as a dependable technique for determining the gender of an individual. The Visual Geometry Group 16 (VGG16) and Visual Geometry Group 19 (VGG19) algorithms have been proven to be effective in image classification. To acknowledge the importance of comprehending the complex procedures associated with the generation and adjustment of inputs in order to obtain precise outcomes using the VGG16 and VGG19 algorithms. The current work utilised a dataset including 274 cephalometric radiographic pictures of adult Indonesians' oral health records to construct a gender classification model using the VGG16 and VGG19 architectures using Python. The VGG16 model has a gender identification accuracy of 93% for females and 73% for males, resulting in an average accuracy of 89% across both genders. In the context of gender identification, the VGG19 model has been found to achieve an accuracy of 0.95% for females and 0.80% for men, resulting in an overall accuracy of 0.93% when considering both genders. The application of VGG16 and VGG19 models has played a significant role in identifying gender based on the study of cephalometric radiography. This application has demonstrated the exceptional effectiveness of both models in accurately predicting the gender of Indonesian adults.

Deceiving Humans and Machines Alike: Search-based Test Input Generation for DNNs Using Variational Autoencoders

Due to the rapid adoption of Deep Neural Networks (DNNs) into larger software systems, testing of DNN-based systems has received much attention recently. While many different test adequacy criteria have been suggested, we lack effective test input generation techniques. Inputs such as images of real-world objects and scenes are not only expensive to collect but also difficult to randomly sample. Consequently, current testing techniques for DNNs tend to apply small local perturbations to existing inputs to generate new inputs. We propose SINVAD (Search-based Input space Navigation using Variational AutoencoDers), a way to sample from, and navigate over, a space of realistic inputs that resembles the true distribution in the training data. Our input space is constructed using Variational Autoencoders (VAEs), and navigated through their latent vector space. Our analysis shows that the VAE-based input space is well-aligned with human perception of what constitutes realistic inputs. Further, we show that this space can be effectively searched to achieve various testing scenarios, such as boundary testing of two different DNNs or analyzing class labels that are difficult for the given DNN to distinguish. Guidelines on how to design VAE architectures are presented as well. Our results have the potential to open the field to meaningful exploration through the space of highly structured images.

On Input Generators for Cyber–Physical Systems Falsification

On Input Generators for Cyber–Physical Systems Falsification

DiPri : Distance-based Seed Prioritization for Greybox Fuzzing

Greybox fuzzing is a powerful testing technique. Given a set of initial seeds, greybox fuzzing continuously generates new test inputs to execute the program under test and drives executions with code coverage as feedback. Seed prioritization is an important step of greybox fuzzing that helps greybox fuzzing choose promising seeds for input generation in priority. However, mainstream greybox fuzzers like AFL++ and Zest tend to neglect the importance of seed prioritization. They may pick seeds plainly according to the sequential order of the seeds being queued or an order produced with a random-based approach, which may consequently degrade their performance in exploring code and exposing bugs. In the meantime, existing state-of-the-art techniques like Alphuzz and K-Scheduler adopt complex strategies to schedule seeds. Although powerful, such strategies also inevitably incur great overhead and will reduce the scalability of the proposed technique. In this paper, we propose a novel distance-based seed prioritization approach named DiPri to facilitate greybox fuzzing. Specifically, DiPri evaluates the queued seeds according to seed distances and chooses the outlier ones, which are the farthest from the others, in priority to improve the probabilities of discovering previously unexplored code regions. To make a profound evaluation of DiPri , we prototype DiPri on AFL++ and conduct large-scale experiments with four baselines and 24 C/C++ fuzz targets, where eight are from widely adopted real-world projects, eight are from the coverage-based benchmark FuzzBench, and eight are from the bug-based benchmark Magma. The results obtained through a fuzzing exceeding 50,000 CPU hours suggest that DiPri can (1) insignificantly influence the host fuzzer’s capability of code coverage by slightly improving the branch coverage on the eight targets from real-world projects and slightly reducing the branch coverage on the eight targets from FuzzBench, and (2) improve the host fuzzer’s capability of finding bugs by triggering five more Magma bugs. Besides the evaluation with the three C/C++ benchmarks, we integrate DiPri into the Java fuzzer Zest and conduct experiments on a Java benchmark composed of five real-world programs for more than 8,000 CPU hours to empirically study the scalability of DiPri . The results with the Java benchmark demonstrate that DiPri is pretty scalable and can help the host fuzzer find bugs more consistently.

Simulation of Human Movement in Zero Gravity.

In the era of expanding manned space missions, understanding the biomechanical impacts of zero gravity on human movement is pivotal. This study introduces a novel and cost-effective framework that demonstrates the application of Microsoft's Azure Kinect body tracking technology as a motion input generator for subsequent OpenSim simulations in weightlessness. Testing rotations, locomotion, coordination, and martial arts movements, we validate the results' realism under the constraints of angular and linear momentum conservation. While complex, full-body coordination tasks face limitations in a zero gravity environment, our findings suggest possible approaches to device-free exercise routines for astronauts and reveal insights into the feasibility of hand-to-hand combat in space. However, some challenges remain in distinguishing zero gravity effects in the simulations from discrepancies in the captured motion input or forward dynamics calculations, making a comprehensive validation difficult. The paper concludes by highlighting the framework's practical potential for the future of space mission planning and related research endeavors, while also providing recommendations for further refinement.

Fatty acid composition and metabolic pathways in Arbacia dufresnii (Arbaciidae: Arbacioida) gametes: implications of shrimp byproducts in aquaculture feeds

Introduction: Care towards nutrition is essential for the quality of a sustainable aquaculture product. Since the balance in food affects the growth and production of gametes. The circular economy is made possible through the use of discarded materials.
 Objective: The aim of this research was to study the fatty acid composition and metabolic pathways in the gametes of Arbacia dufresnii, with a focus on the implications of incorporating shrimp byproducts into aquaculture feeds.
 Methods: Four different treatments were designed to maintain optimal nutritional quality, particularly in lipids and proteins, based on previous studies. The fatty acid profiles of the feeds and gametes were analyzed by using gas-chromatography, and statistical analyses were conducted to determine significant differences.
 Results: Significant differences were observed in the abundance (%) of omega-3 (ω-3) and omega-6 (ω-6) fatty acids. The (ω-3) metabolic pathway was more pronounced in the gametes of wild animals and those fed with the experimental feeds. In contrast, the (ω-6) metabolic pathway was less relevant in these groups. The (ω-3) /(ω-6) ratio was highest in the gametes of wild animals. Feeds enriched in fatty acids enhanced their bioaccumulation in the gametes reaching higher concentrations than wild animals. The availability of fatty acids in foods allowed their bioaccumulation in gametes, with concentrations equal to or higher than those observed in animals in their natural environment for certain fatty acids.
 Conclusions: Incorporating shrimp byproducts in aquaculture feeds demonstrated a promising strategy for resource utilization and organic input generation. The fatty acid composition in the gametes of A. dufresnii was influenced by the diet, highlighting the potential of balanced feeds to enhance the bioaccumulation of essential fatty acids. These findings provide valuable insights for the development of sustainable aquaculture practices and the production of nutritionally enriched seafood products.

AI Application in Foreign Language Literature: ChatGPT's Impact and Skill Enhancement

This study investigates the prospective of incorporating input hypothesis, output hypothesis, interaction hypothesis and metacognitive theory into the best practices of ChatGPT in foreign literature. The study used an online survey involving 146 Chinese internet users to examine opinions on the use of ChatGPT for foreign literature analysis and tasks. Specific skills enhanced by AI integration, such as critical thinking, nuanced comprehension, and advanced linguistic proficiency in foreign languages are discussed in the research. However, there were concerns about its ethical implications when used for literary purposes because it may lead to biases, wrong information and risks which include plagiarism. During the application of ChatGPT, it was emphasized that comprehensible input is crucial to ensure that AI provided content is both understandable and suitable to learners’ current proficiency level. Moreover, learners are encouraged to actively utilize ChatGPT as feedback as well as correction tool. Furthermore, this research allowed learners to engage in live communication through using ChatGPT as a speaking partner thereby negotiating meaning and getting instant feedback to support interaction hypothesis (IH). Underpinned by metacognitive theory, instructing learners to reflect on their learning process with the help of ChatGPT involves identifying areas of difficulty and seeking specific assistance, for example, learners may ask about linguistic doubts from chat GTP or test their understanding about certain concepts or vocabulary using it. In order to effectively integrate these hypotheses with metacognitive theories, interactive chat GPTs were designed which required learners’ involvement in comprehensible input generation of language, output meaningful interactions and reflection on learning process; reading or listening to foreign language content (input), responding or creating content (output), engaging in conversation (interaction) tasks are assessed for their comprehension and performance levels (metacognition).

A 4-channelled hazy image input generation and deep learning-based single image dehazing

The images in foggy weather are often degraded which may affect the object detection process. Hence, in recent times, several schemes have been designed to eliminate the haze effect and enhance the performance of computer vision systems. Although these methods reduce the haze effect, they also produce over-saturation and over-degradation on most occasions. These problems occur due to inadequate utilization of the regional haze properties during the dehazing process. Therefore, a new dehazing model is proposed in this paper to address the issues faced by existing dehazing algorithms. The residual convolutional neural network (RCNN) with 14 layers is developed in the present work. In this model, features to indicate the extent of haze are extracted using the regional characteristics of a hazy image and are used as the fourth channel along with the three colour channels of a hazy image. The proposed RCNN is trained with 4-channel hazy images as input and their corresponding haze-free images as output. The results of our model are obtained with several images taken from three different datasets. Through the experimentation, quantitative and qualitative improvements are observed when compared to state-of-the-art dehazing methods.

Optimal test case generation for boundary value analysis

Boundary value analysis (BVA) is a common technique in software testing that uses input values that lie at the boundaries where significant changes in behavior are expected. This approach is widely recognized and used as a natural and effective strategy for testing software. Test coverage is one of the criteria to measure how much the software execution paths are covered by the set of test cases. This paper focuses on evaluating test coverage with respect to BVA by defining a metric called boundary coverage distance (BCD). The BCD metric measures the extent to which a test set covers the boundaries. In addition, based on BCD, we consider the optimal test input generation to minimize BCD under the random testing scheme. We propose three algorithms, each representing a different test input generation strategy, and evaluate their fault detection capabilities through experimental validation. The results indicate that the BCD-based approach has the potential to generate boundary values and improve the effectiveness of software testing.

GEO4PALM v1.1: an open-source geospatial data processing toolkit for the PALM model system

Abstract. A geospatial data processing tool, GEO4PALM, has been developed to generate geospatial static input for the Parallelized Large-Eddy Simulation (PALM) model system. PALM is a community-driven large-eddy simulation model for atmospheric and environmental research. Throughout PALM's 20-year development, research interests have been increasing in its application to realistic conditions, especially for urban areas. For such applications, geospatial static input is essential. Although abundant geospatial data are accessible worldwide, geospatial data availability and quality are highly variable and inconsistent. Currently, the geospatial static input generation tools in the PALM community heavily rely on users for data acquisition and pre-processing. New PALM users face large obstacles, including significant time commitments, to gain the knowledge needed to be able to pre-process geospatial data for PALM. Expertise beyond atmospheric and environmental research is frequently needed to understand the data sets required by PALM. Here, we present GEO4PALM, which is a free and open-source tool. GEO4PALM helps users generate PALM static input files with a simple, homogenised, and standardised process. GEO4PALM is compatible with geospatial data obtained from any source, provided that the data sets comply with standard geo-information formats. Users can either provide existing geospatial data sets or use the embedded data interfaces to download geo-information data from free online sources for any global geographic area of interest. All online data sets incorporated in GEO4PALM are globally available, with several data sets having the finest resolution of 1 m. In addition, GEO4PALM provides a graphical user interface (GUI) for PALM domain configuration and visualisation. Two application examples demonstrate successful PALM simulations driven by geospatial input generated by GEO4PALM using different geospatial data sources for Berlin, Germany, and Ōtautahi / Christchurch, New Zealand. GEO4PALM provides an easy and efficient way for PALM users to configure and conduct PALM simulations for applications and investigations such as urban heat island effects, air pollution dispersion, renewable energy resourcing, and weather-related hazard forecasting. The wide applicability of GEO4PALM makes PALM more accessible to a wider user base in the scientific community.

О генерической сложности проблемы вычисления функции Эйлера

We study the generic complexity of the problem of the Euler function computation. This problem has important applications in modern cryptography. For example, the cryptographic strength of the famous public key encryption system RSA is based on the assumption of its hardness. We prove that under the condition of worst-case hardness and P = BPP there is no polynomial strongly generic algorithm for this problem. For a strongly generic polynomial algorithm, there is no efficient method for random generation of inputs on which the algorithm cannot solve the problem. Thus, this result justifies the application of the problem of computing the Euler function in public key cryptography. To prove this theorem, we use the method of generic amplification, which allows us to construct generically hard problems from the problems that are hard in the classical sense. The main feature of this method is the cloning technique, which combines the input data of a problem into sufficiently large sets of equivalent input data. Equivalence is understood in the sense that the problem is solved in a similar way for them.

A Proposal of Code Writing Problem for C Programming Learning Assistant System

C programming has been a fundamental subject for a lot of university students studying programming lan guages, algorithms, and computer architecture. To enhance C programming education in schools, we have developed the C Programming Learning Assistant System (CPLAS) which provides a variety of programming assignments to cover different learning stages. The programming assignments offered by CPLAS allow the students to practice writing partial source code to learn grammar, code reading, and code debugging skills. However, the current assignments offered by CPLAS do not cover students to practice writing the whole C source code from scratch. Therefore, in this paper, we propose the Code Writing Problem (CWP) for students to write the C source code from scratch. In a CWP instance, a problem statement, an input list, and an expected output are given to the students. The students need to write the C source code from scratch by referring to the given information. The answer codes are marked through 1) compiling test, 2) execution test, and 3) output test. To avoid cheating by students, we use the random input generation method for each data type. To evaluate the proposal, we generated and assigned 11 CWP instances to the students. From their solution results, 10 out of 11 CWP instances achieved over 78% correct answer rate, and the feedback from the students confirmed the validity of the proposal.