Explore the vast range of titles available.

State-of-the-art neural networks build an internal model of the training data, tailored to a given classification task. The study of such a model is of interest, and therefore, research on explainable artificial intelligence (XAI) aims at investigating if, in the internal states of a network, it is possible to identify rules that associate data to their corresponding classification. This work moves toward XAI research on neural networks trained in the classification of source code snippets, in the specific domain of cybersecurity. In this context, typically, textual instances have firstly to be encoded with non-invertible transformation into numerical vectors to feed the models, and this limits the applicability of known XAI methods based on the differentiation of neural signals with respect to real valued instances. In this work, we start from the known TCAV method, designed to study the human understandable concepts that emerge in the internal layers of a neural network, and we adapt it to transformers architectures trained in solving source code classification problems. We first determine domain-specific concepts (e.g., the presence of given patterns in the source code), and for each concept, we train support vector classifiers to separate points in the vector activation spaces that represent input instances with the concept from those without the concept. Then, we study if the presence (or the absence) of such concepts affects the decision process of the neural network. Finally, we discuss about how our approach contributes to general XAI goals and we suggest specific applications in the source code analysis field.

Deep neural networks have proven to be able to learn rich internal representations, including for features that can also be used for different purposes than those the networks are originally developed for. In this paper, we are interested in exploring such ability and, to this aim, we propose a novel approach for investigating the internal behavior of networks trained for source code processing tasks. Using a simple autoencoder trained in the reconstruction of vectors representing programs (i.e., program embeddings), we first analyze the performance of the internal neurons in classifying programs according to different labeling policies inspired by real programming issues, showing that some neurons can actually detect different program properties. We then study the dynamics of the network from an information-theoretic standpoint, namely by considering the neurons as signaling systems and by computing the corresponding entropy. Further, we define a way to distinguish neurons according to their behavior, to consider them as formally associated with different abstract concepts, and through the application of nonparametric statistical tests to pairs of neurons, we look for neurons with unique (or almost unique) associated concepts, showing that the entropy value of a neuron is related to the rareness of its concept. Finally, we discuss how the proposed approaches for ranking the neurons can be generalized to different domains and applied to more sophisticated and specialized networks so as to help the research in the growing field of explainable artificial intelligence.

As the prevalence and sophistication of cyber threats continue to increase, the development of robust vulnerability detection techniques becomes paramount in ensuring the security of computer systems. Neural models have demonstrated significant potential in identifying vulnerabilities; however, they are not immune to adversarial attacks. This paper presents a set of evolutionary techniques for generating adversarial instances to enhance the resilience of neural models used for vulnerability detection. The proposed approaches leverage an evolution strategy (ES) algorithm that utilizes as the fitness function the output of the neural network to deceive. By starting from existing instances, the algorithm evolves individuals, represented by source code snippets, by applying semantic-preserving transformations, while utilizing the fitness to invert their original classification. This iterative process facilitates the generation of adversarial instances that can mislead the vulnerability detection models while maintaining the original behavior of the source code. The significance of this research lies in its contribution to the field of cybersecurity by addressing the need for enhanced resilience against adversarial attacks in vulnerability detection models. The evolutionary approach provides a systematic framework for generating adversarial instances, allowing for the identification and mitigation of weaknesses in AI classifiers.

Taking inspiration from some laws of Nature—energy transformation and chemical reactions—we consider two different paradigms of computation in the framework of Membrane Computing. We first study the computational power of energy-based P systems, a model of membrane systems where a fixed amount of energy is associated with each object and the rules transform objects by manipulating their energy. We show that if we assign local priorities to the rules, then energy-based P systems are as powerful as Turing machines; otherwise, they can be simulated by vector addition systems, and hence are not universal. Then, we consider stochastic membrane systems where computations are performed through chemical networks. We show how molecular species and chemical reactions can be used to describe and simulate the functioning of Fredkin gates and circuits. We conclude the paper with some research topics related to computing with energy-based P systems and with chemical reactions.

Understanding source code is a topic of great interest in the software engineering community, since it can help programmers in various tasks such as software maintenance and reuse. Recent advances in large language models (LLMs) have demonstrated remarkable program comprehension capabilities, while transformer-based topic modeling techniques offer effective ways to extract semantic information from text. This paper proposes and explores a novel approach that combines these strengths to automatically identify meaningful topics in a corpus of Python programs. Our method consists in applying topic modeling on the descriptions obtained by asking an LLM to summarize the code. To assess the internal consistency of the extracted topics, we compare them against topics inferred from function names alone, and those derived from existing docstrings. Experimental results suggest that leveraging LLM-generated summaries provides interpretable and semantically rich representation of code structure. The promising results suggest that our approach can be fruitfully applied in various software engineering tasks such as automatic documentation and tagging, code search, software reorganization and knowledge discovery in large repositories.

We investigate polarizationless P systems with active membranes working in maximally parallel manner, which do not make use of evolution or communication rules, in order to find which features are sufficient to efficiently solve computationally hard problems. We show that such systems are able to solve the PSPACE -complete problem Quantified 3-sat , provided that non-elementary membrane division is controlled by the presence of a (possibly non-elementary) membrane.

In this paper, we propose a novel approach for mining different program features by analysing the internal behaviour of a deep neural network trained on source code. Using an unlabelled dataset of Java programs and three different embedding strategies for the methods in the dataset, we train an autoencoder for each program embedding and then we test the emerging ability of the internal neurons in autonomously building internal representations for different program features. We defined three binary classification labelling policies inspired by real programming issues, so to test the performance of each neuron in classifying programs accordingly to these classification rules, showing that some neurons can actually detect different program properties. We also analyse how the program representation chosen as input affects the performance on the aforementioned tasks. On the other hand, we are interested in finding the overall most informative neurons in the network regardless of a given task. To this aim, we propose and evaluate two methods for ranking neurons independently of any property. Finally, we discuss how these ideas can be applied in different settings for simplifying the programmers' work, for instance if included in environments such as software repositories or code editors.

FLASH Radiotherapy (RT) is a potentially new cancer radiotherapy technique where an entire therapeutic dose is delivered in about 0.1 s and at ~1000 times higher dose rate than in conventional RT. For clinical trials to be conducted safely, precise and fast beam monitoring that can generate an out-of-tolerance beam interrupt is required. A FLASH Beam Scintillator Monitor (FBSM) is being developed based in part on a novel proprietary inorganic hybrid scintillator material. The FBSM provides large area coverage, low mass profile, linear response over a broad dynamic range, radiation tolerance, and real-time analysis IEC-compliant fast beam-interrupt signal. This paper includes the design concept and test results from a prototype device in radiation beams that include heavy ions, FLASH level dose per pulse electron beams, anda hospital radiotherapy clinic with electron beams. Results include image quality, response linearity, radiation hardness, spatial resolution, and real-time data processing. The scintillator showed a small -0.02%/kGy signal decrease after a 212 kGy cumulative dose resulting from continuous exposure for 15 minutes at a FLASH compatible dose rate of 234 Gy/s. These tests established the linear response of the FBSM with respect to dose per pulse. Comparison with commercial Gafchromic film indicates that the FBSM produces a high resolution 2D beam image and can reproduce a nearly identical beam profile. At 20 kfps or 50 microsec/frame, the real-time FPGA based computation and analysis of beam position, beam shape, and beam dose takes < 1 microsec.

FLASH Radiotherapy (RT) is an emergent cancer radiotherapy modality where an entire therapeutic dose is delivered at more than 1000 times higher dose rate than conventional RT. For clinical trials to be conducted safely, a precise and fast beam monitor that can generate out-of-tolerance beam interrupts is required. This paper describes the overall concept and provides results from a prototype ultra-fast, scintillator-based beam monitor for both proton and electron beam FLASH applications. A FLASH Beam Scintillator Monitor (FBSM) is being developed that employs a novel proprietary scintillator material. The FBSM has capabilities that conventional RT detector technologies are unable to simultaneously provide: 1) large area coverage; 2) a low mass profile; 3) a linear response over a broad dynamic range; 4) radiation hardness; 5) real-time analysis to provide an IEC-compliant fast beam-interrupt signal based on true two-dimensional beam imaging, radiation do-simetry and excellent spatial resolution. The FBSM uses a proprietary low mass, less than 0.5 mm water equivalent, non-hygroscopic, radiation tolerant scintillator material (designated HM: hybrid material) that is viewed by high frame rate CMOS cameras. Folded optics using mirrors enable a thin monitor profile of ~10 cm. A field programmable gate array (FPGA) data acquisition system (DAQ) generates real-time analysis on a time scale appropriate to the FLASH RT beam modality: 100-1000 Hz for pulsed electrons and 10-20 kHz for quasi-continuous scanning proton pencil beams. An ion beam monitor served as the initial development platform for this work and was tested in low energy heavy-ion beams ( Kr and protons). A prototype FBSM was fabricated and then tested in various radiation beams that included FLASH level dose per pulse electron beams, and a hospital radiotherapy clinic with electron beams. Results presented in this report include image quality, response linearity, radiation hardness, spatial resolution, and real-time data processing. The HM scintillator was found to be highly radiation damage resistant. It exhibited a small 0.025%/kGy signal decrease from a 216 kGy cumulative dose resulting from continuous exposure for 15 minutes at a FLASH compatible dose rate of 237 Gy/s. Measurements of the signal amplitude vs beam fluence demonstrate linear response of the FBSM at FLASH compatible dose rates of > 40 Gy/s. Comparison with commercial Gafchromic film indicates that the FBSM produces a high resolution 2D beam image and can reproduce a nearly identical beam profile, including primary beam tails. The spatial resolution was measured at 35-40 μm. Tests of the firmware beta version show successful operation at 20,000 Hz frame rate or 50 μs/frame, where the real-time analysis of the beam parameters is achieved in less than 1 μs. The FBSM is designed to provide real-time beam profile monitoring over a large active area without significantly degrading the beam quality. A prototype device has been staged in particle beams at currents of single particles up to FLASH level dose rates, using both continuous ion beams and pulsed electron beams. Using a novel scintillator, beam profiling has been demonstrated for currents extending from single particles to 10 nA currents. Radiation damage is minimal and even under FLASH conditions would require ≥ 50 kGy of accumulated exposure in a single spot to result in a 1% decrease in signal output. Beam imaging is comparable to radiochromic films, and provides immediate images without hours of processing. Real-time data processing, taking less than 50 μs (combined data transfer and analysis times), has been implemented in firmware for 20 kHz frame rates for continuous proton beams.

We consider the structure of the intestinal epithelial tissue and of cell–cell junctions as the biological model inspiring a new class of P systems. First we define the concept of cell polarity, a formal property derived from epithelial cells, which present morphologically and functionally distinct regions of the plasma membrane. Then we show two preliminary results for this new model of computation: on the theoretical side, we show that P systems with cell polarity are computationally (Turing) complete; on the modelling side, we show that the transepithelial movement of glucose from the intestinal lumen into the blood can be described by such a formal system. Finally, we define tissue P systems with cell polarity, where each cell has fixed connections to the neighbouring cells and to the environment, according to both the cell polarity and specific cell–cell junctions.