Publicação
Automated LLM exploit generation framework (ALEGF)
| datacite.subject.sdg | 09:Indústria, Inovação e Infraestruturas | |
| datacite.subject.sdg | 16:Paz, Justiça e Instituições Eficazes | |
| datacite.subject.sdg | 04:Educação de Qualidade | |
| dc.contributor.author | Guerreiro, Joel | |
| dc.contributor.author | João Santos | |
| dc.date.accessioned | 2026-07-23T10:52:00Z | |
| dc.date.available | 2026-07-23T10:52:00Z | |
| dc.date.issued | 2026 | en_US |
| dc.date.updated | 2026-07-23T10:24:48Z | |
| dc.description.abstract | Software development frequently suffer from programming defects, mistakes and design flaws introducing critical security vulnerabilities. These weaknesses can be exploited causing significant operational disruption and organizational losses. Identifying and exploiting such vulnerabilities is a complex task that requires binary or source code detailed analysis, operating systems deep knowledge, file system formats and processor architectures, as well as expertise in multiple techniques. Traditional Automatic Exploit Generation (AEG) approaches rely on symbolic execution, fuzzing and heuristicbased methods. In this paper, an automated framework is presented and designed to evaluate Large Language Models (LLMs) to detect vulnerabilities and generate exploits without human intervention. The framework operates within a controlled, sandboxed and fully reproducible environment to prevent real-word security risks while enabling systematic experimentation. The objective is to assess whether LLMs can serve as auxiliary tools for software security testing and vulnerability analysis. The results provide insights into the feasibility, limitations and potential LLM-driven automated exploitation, yet not competitive with AEG tools state-of-the-art. | eng |
| dc.description.version | info:eu-repo/semantics/publishedVersion | |
| dc.identifier.doi | 10.1007/978-3-032-29653-5_23 | en_US |
| dc.identifier.isbn | 978-3-032-29652-8 | |
| dc.identifier.slug | cv-prod-5071103 | |
| dc.identifier.uri | http://hdl.handle.net/10400.1/29296 | |
| dc.language.iso | eng | |
| dc.peerreviewed | yes | |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
| dc.title | Automated LLM exploit generation framework (ALEGF) | eng |
| dc.type | book part | en_US |
| dspace.entity.type | Publication | |
| oaire.citation.endPage | 379 | |
| oaire.citation.startPage | 366 | |
| oaire.citation.title | Lecture Notes in Computer Science | |
| oaire.citation.volume | 16710 | |
| oaire.version | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |
| person.familyName | Guerreiro | |
| person.givenName | Joel | |
| person.givenName | João Santos | |
| person.identifier.ciencia-id | 0413-5074-579C | |
| person.identifier.orcid | 0000-0001-7471-4928 | |
| person.identifier.orcid | 0009-0000-4071-2473 | |
| person.identifier.rid | AAS-6766-2020 | |
| person.identifier.scopus-author-id | 57201942074 | |
| rcaap.cv.cienciaid | 0413-5074-579C | Joel David Valente Guerreiro | |
| rcaap.rights | openAccess | en_US |
| relation.isAuthorOfPublication | 1e937f3a-16db-40b1-820a-2733a9a6fbae | |
| relation.isAuthorOfPublication | a38dcd50-408c-49b9-9dc7-0bbda29d9ae4 | |
| relation.isAuthorOfPublication.latestForDiscovery | 1e937f3a-16db-40b1-820a-2733a9a6fbae |