Zitieren Sie bitte immer diesen URN: urn:nbn:de:kobv:b43-651357

An illumination based backdoor attack against crack detection systems in laser beam welding

  • Deep neural networks (DNNs) have been wildly used in engineering and have achieved state-of-the-art performance in prediction and measurement tasks. A solidification crack is a serious fault during laser beam welding and it has been proven to be successfully detected using DNNs. Recently, research on the security of DNNs is receiving increasing attention because it is necessary to explore the reliability of DNNs to avoid potential security risks. The backdoor attack is a serious threat, where attackers aim to inject an inconspicuous pattern referred to as trigger into a small portion of training data, resulting in incorrect predictions in the reference phase whenever the input contains the trigger. In this work, we first generate experimental data containing actual cracks in the welding laboratory for training a crack detection model. Then, targeting this scenario, we design a new type of backdoor attack to induce the model to predict the crack as a normal state. Considering theDeep neural networks (DNNs) have been wildly used in engineering and have achieved state-of-the-art performance in prediction and measurement tasks. A solidification crack is a serious fault during laser beam welding and it has been proven to be successfully detected using DNNs. Recently, research on the security of DNNs is receiving increasing attention because it is necessary to explore the reliability of DNNs to avoid potential security risks. The backdoor attack is a serious threat, where attackers aim to inject an inconspicuous pattern referred to as trigger into a small portion of training data, resulting in incorrect predictions in the reference phase whenever the input contains the trigger. In this work, we first generate experimental data containing actual cracks in the welding laboratory for training a crack detection model. Then, targeting this scenario, we design a new type of backdoor attack to induce the model to predict the crack as a normal state. Considering the stealthiness of the attack, a common phenomenon during the welding process, illumination, is used as the backdoor trigger. Experimental results demonstrate that the proposed method can successfully attack the crack detection system and achieve over 90% attack success rate on the test set.zeige mehrzeige weniger

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar Anzahl der Zugriffe auf dieses Dokument
Metadaten
Autor*innen:Wenjie Huo, Lennart Schmies, Andrey GumenyukORCiD, Michael RethmeierORCiD, Katinka WolterORCiD
Dokumenttyp:Beitrag zu einem Tagungsband
Veröffentlichungsform:Graue Literatur
Sprache:Englisch
Titel des übergeordneten Werkes (Englisch):Machine learning for cyber physical systems : proceedings of the conference ML4CPS 2025
Jahr der Erstveröffentlichung:2025
Organisationseinheit der BAM:9 Komponentensicherheit
9 Komponentensicherheit / 9.3 Schweißtechnische Fertigungsverfahren
Veröffentlichende Institution:Bundesanstalt für Materialforschung und -prüfung (BAM)
Verlag:Universitätsbibliothek der HSU/UniBw H
Verlagsort:Hamburg
Jahrgang/Band:2025
Erste Seite:12
Letzte Seite:21
DDC-Klassifikation:Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Ingenieurwissenschaften und zugeordnete Tätigkeiten
Freie Schlagwörter:Backdoor attack; Deep neural networks; System security; Welding crack detection
Themenfelder/Aktivitätsfelder der BAM:Material
Material / Degradationsmechanismen
Veranstaltung:8th ML4CPS 2025 – Machine Learning for Cyber-Physical Systems
Veranstaltungsort:Berlin, Germany
Beginndatum der Veranstaltung:06.03,2025
Enddatum der Veranstaltung:07.03.2025
DOI:10.24405/20021
URN:urn:nbn:de:kobv:b43-651357
Verfügbarkeit des Dokuments:Datei für die Öffentlichkeit verfügbar ("Open Access")
Lizenz (Deutsch):License LogoCreative Commons - CC BY - Namensnennung 4.0 International
Datum der Freischaltung:15.12.2025
Referierte Publikation:Nein
Schriftenreihen ohne Nummerierung:Wissenschaftliche Artikel der BAM
Einverstanden
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.