no code implementations • 29 Apr 2024 • Norbert Tihanyi, Tamas Bisztray, Mohamed Amine Ferrag, Ridhi Jain, Lucas C. Cordeiro
This study provides a comparative analysis of state-of-the-art large language models (LLMs), analyzing how likely they generate vulnerabilities when writing simple C programs using a neutral zero-shot prompt.
no code implementations • 14 Apr 2024 • Víctor A. Braberman, Flavia Bonomo-Braberman, Yiannis Charalambous, Juan G. Colonna, Lucas C. Cordeiro, Rosiane de Freitas
Prompting has become one of the main approaches to leverage emergent capabilities of Large Language Models [Brown et al. NeurIPS 2020, Wei et al. TMLR 2022, Wei et al. NeurIPS 2022].
1 code implementation • 7 Sep 2023 • Edoardo Manino, Rafael Sá Menezes, Fedor Shmarov, Lucas C. Cordeiro
Safety-critical systems with neural network components require strong guarantees.
no code implementations • 13 Jul 2023 • Mohamed Amine Ferrag, Ammar Battah, Norbert Tihanyi, Merouane Debbah, Thierry Lestable, Lucas C. Cordeiro
Software vulnerabilities leading to various detriments such as crashes, data loss, and security breaches, significantly hinder the quality, affecting the market adoption of software applications and systems.
no code implementations • 5 Jul 2023 • Norbert Tihanyi, Tamas Bisztray, Ridhi Jain, Mohamed Amine Ferrag, Lucas C. Cordeiro, Vasileios Mavroeidis
This paper presents the FormAI dataset, a large collection of 112, 000 AI-generated compilable and independent C programs with vulnerability classification.
no code implementations • 25 Jun 2023 • Mohamed Amine Ferrag, Mthandazo Ndhlovu, Norbert Tihanyi, Lucas C. Cordeiro, Merouane Debbah, Thierry Lestable, Narinderjit Singh Thandi
The field of Natural Language Processing (NLP) is currently undergoing a revolutionary transformation driven by the power of pre-trained Large Language Models (LLMs) based on groundbreaking Transformer architectures.
no code implementations • 23 Jun 2023 • Xidan Song, Youcheng Sun, Mustafa A. Mustafa, Lucas C. Cordeiro
It accepts the full-precision and weight-quantized neural networks and a repair dataset of passing and failing tests.
1 code implementation • 24 May 2023 • Yiannis Charalambous, Norbert Tihanyi, Ridhi Jain, Youcheng Sun, Mohamed Amine Ferrag, Lucas C. Cordeiro
In this paper we present a novel solution that combines the capabilities of Large Language Models (LLMs) with Formal Verification strategies to verify and automatically repair software vulnerabilities.
no code implementations • 21 Mar 2023 • Mohamed Amine Ferrag, Burak Kantarci, Lucas C. Cordeiro, Merouane Debbah, Kim-Kwang Raymond Choo
However, we need to also consider the potential of attacks targeting the underlying AI systems (e. g., adversaries seek to corrupt data on the IoT devices during local updates or corrupt the model updates); hence, in this article, we propose an anticipatory study for poisoning attacks in federated edge learning for digital twin 6G-enabled IoT environments.
1 code implementation • 22 Jan 2023 • Tong Wu, Edoardo Manino, Fatimah Aljaafari, Pavlos Petoumenos, Lucas C. Cordeiro
We describe and evaluate LF-checker, a metaverifier tool based on machine learning.
no code implementations • 9 Jul 2022 • João Batista P. Matos Jr., Iury Bessa, Edoardo Manino, Xidan Song, Lucas C. Cordeiro
Existing quantization techniques tend to degrade the network accuracy.
1 code implementation • 30 Jul 2019 • Luiz H. Sena, Iury V. Bessa, Mikhail R. Gadelha, Lucas C. Cordeiro, Edjard Mota
Artificial Neural networks (ANNs) are powerful computing systems employed for various applications due to their versatility to generalize and to respond to unexpected inputs/patterns.
no code implementations • 14 Aug 2017 • Rodrigo F. Araújo, Alexandre Ribeiro, Iury V. Bessa, Lucas C. Cordeiro, João E. C. Filho
We describe and evaluate a novel optimization-based off-line path planning algorithm for mobile robots based on the Counterexample-Guided Inductive Optimization (CEGIO) technique.
no code implementations • 11 Apr 2017 • Rodrigo F. Araujo, Higo F. Albuquerque, Iury V. de Bessa, Lucas C. Cordeiro, Joao Edgar C. Filho
This paper describes three variants of a counterexample guided inductive optimization (CEGIO) approach based on Satisfiability Modulo Theories (SMT) solvers.