João Lourenço

Ricardo Bessa, Rui Claro, João Trindade et al.

Large Language Models (LLMs) are redefining offensive cybersecurity by allowing the generation of harmful machine code with minimal human intervention. While attackers take advantage of dark LLMs such as XXXGPT and WolfGPT to produce malicious code, ethical hackers can follow similar approaches to automate traditional pentesting workflows. In this work, we present RedShell, a privacy-preserving, hardware-efficient framework that leverages fine-tuned LLMs to assist pentesters in generating offensive PowerShell code targeting Microsoft Windows vulnerabilities. RedShell was trained on a malicious PowerShell dataset from the literature, which we further enhanced with manually curated code samples. Experiments show that our framework achieves over 90% syntactic validity in generated samples and strong semantic alignment with reference pentesting snippets, outperforming state-of-the-art counterparts in distance metrics such as edit distance (above 50% average code similarity). Additionally, functional experiments emphasize the execution reliability of the snippets produced by RedShell in a testing scenario that mirrors real-world settings. This work sheds light on the state-of-the-art research in the field of Generative AI applied to malicious code generation and automated testing, acknowledging the potential benefits that LLMs hold within controlled environments such as pentesting.

Ricardo Bessa, Rui Claro, João Trindade et al.

The application of Machine Learning techniques in code generation is now a common practice for most developers. Tools such as ChatGPT from OpenAI leverage the natural language processing capabilities of Large Language Models to generate machine code from natural language descriptions. In the cybersecurity field, red teams can also take advantage of generative models to build malicious code generators, providing more automation to Pentest audits. However, the application of Large Language Models in malicious code generation remains challenging due to the lack of data to train and evaluate offensive code generators. In this work, we propose RedShell, a tool that allows ethical hackers to generate malicious PowerShell code. We also introduce a ground truth dataset, combining publicly available code samples to fine-tune models in malicious PowerShell generation. Our experiments demonstrate the strong capabilities of RedShell in generating syntactically valid PowerShell, with fewer than 10% of the generated samples resulting in parse errors. Furthermore, our specialized model was able to produce samples that were semantically consistent with reference snippets, achieving a competitive performance on standard output similarity metrics such as Edit Distance and METEOR, with their mean similarity scores exceeding 50% and 40%, respectively. This work sheds light on the state-of-the-art research in the field of Generative AI applied to Pentesting, and also serves as a steppingstone for future advancements, highlighting the potential benefits these models hold within such controlled environments.

Patrícia Monteiro, João Lourenço, António Ravara

--- Portuguese version As falhas de software estão com frequência associadas a acidentes com graves consequências económicas e/ou humanas, pelo que se torna imperioso investir na validação do software, nomeadamente daquele que é crítico. Este artigo endereça a temática da qualidade do software através de uma análise comparativa da usabilidade e eficácia de quatro ferramentas de análise estática de programas em C/C++. Este estudo permitiu compreender o grande potencial e o elevado impacto que as ferramentas de análise estática podem ter na validação e verificação de software. Como resultado complementar, foram identificados novos erros em programas de código aberto e com elevada popularidade, que foram reportados. --- English version Software bugs are frequently associated with accidents with serious economical and/or human consequences, being thus imperative the investment in the validation of software, namely of the critical one. This article addresses the topic of software quality by making a comparative analysis of the usability and efficiency of four static analysis tools for C/C++ programs. This study allow to understand the big potential and high impact that these tools may have in the validation and verification of software. As a complementary result, we identified new errors in very popular open source projects, which have been reported.

Matěj Hejda, Juan Arturo Alanis, Ignacio Ortega-Piwonka et al.

In this work, we introduce an optoelectronic spiking artificial neuron capable of operating at ultrafast rates ($\approx$ 100 ps/optical spike) and with low energy consumption ($<$ pJ/spike). The proposed system combines an excitable resonant tunnelling diode (RTD) element exhibiting negative differential conductance, coupled to a nanoscale light source (forming a master node) or a photodetector (forming a receiver node). We study numerically the spiking dynamical responses and information propagation functionality of an interconnected master-receiver RTD node system. Using the key functionality of pulse thresholding and integration, we utilize a single node to classify sequential pulse patterns and perform convolutional functionality for image feature (edge) recognition. We also demonstrate an optically-interconnected spiking neural network model for processing of spatiotemporal data at over 10 Gbps with high inference accuracy. Finally, we demonstrate an off-chip supervised learning approach utilizing spike-timing dependent plasticity for the RTD-enabled photonic spiking neural network. These results demonstrate the potential and viability of RTD spiking nodes for low footprint, low energy, high-speed optoelectronic realization of neuromorphic hardware.