Skip to main content
Erschienen in:

01.04.2025

A steganographic backdoor attack scheme on encrypted traffic

verfasst von: Bing Rao, Guiqin Zhu, Qiaolong Ding, Dajiang Chen, Mingsheng Cao, Yang Cao, Feiyan Wang

Erschienen in: Peer-to-Peer Networking and Applications | Ausgabe 2/2025

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Der Artikel stellt ein steganographisches Backdoor-Angriffsschema vor, das digitale Steganographie verwendet, um versteckte Trigger in verschlüsselte Verkehrsbilder einzubetten. Indem Trainingsdaten mit diesen Triggern vergiftet werden, kann der Angriff fehlerhaftes Verhalten in neuronalen Netzwerken auslösen, was zu einer Fehlklassifizierung des verschlüsselten Datenverkehrs führt. Die Studie unterstreicht die Durchführbarkeit und Heimlichkeit des Angriffs durch Experimente mit dem ISCXVPN2016-Datensatz und vergleicht ihn mit anderen Backdoor-Angriffsmethoden wie BadNets und Blended-Angriffen. Der Artikel diskutiert auch die Auswirkungen unterschiedlicher Vergiftungsraten auf die Effektivität des Angriffs und das Potenzial der Informationsübertragung durch Hintertüren. Die experimentellen Ergebnisse zeigen die potenziellen Sicherheitsrisiken verschlüsselter Datennetze und die Notwendigkeit robuster Verteidigungsmechanismen.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding, 4171–4186 Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding, 4171–4186
2.
Zurück zum Zitat Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877–1901 Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877–1901
3.
Zurück zum Zitat Wang Q, Xiao P, Li X, Qiu Y, Zheng T, Qin Z (2024) Taas: Trust assessment as a service for secure communication of green edge-assisted uav network. Peer-to-peer Netw Appl, 1–16 Wang Q, Xiao P, Li X, Qiu Y, Zheng T, Qin Z (2024) Taas: Trust assessment as a service for secure communication of green edge-assisted uav network. Peer-to-peer Netw Appl, 1–16
4.
Zurück zum Zitat Victor P, Lashkari AH, Lu R, Sasi T, Xiong P, Iqbal S (2023) Iot malware: An attribute-based taxonomy, detection mechanisms and challenges. Peer-to-peer Netw Appl 16(3):1380–1431CrossRef Victor P, Lashkari AH, Lu R, Sasi T, Xiong P, Iqbal S (2023) Iot malware: An attribute-based taxonomy, detection mechanisms and challenges. Peer-to-peer Netw Appl 16(3):1380–1431CrossRef
5.
Zurück zum Zitat Maarouf R, Sattar D, Matrawy A (2021) Evaluating resilience of encrypted traffic classification against adversarial evasion attacks. In: 2021 IEEE Symposium on Computers and Communications (ISCC), pp 1–6. IEEE Maarouf R, Sattar D, Matrawy A (2021) Evaluating resilience of encrypted traffic classification against adversarial evasion attacks. In: 2021 IEEE Symposium on Computers and Communications (ISCC), pp 1–6. IEEE
6.
Zurück zum Zitat Eykholt K, Evtimov I, Fernandes E, Li B, Rahmati A, Xiao C, Prakash A, Kohno T, Song D (2018) Robust physical-world attacks on deep learning visual classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1625–1634. IEEE Eykholt K, Evtimov I, Fernandes E, Li B, Rahmati A, Xiao C, Prakash A, Kohno T, Song D (2018) Robust physical-world attacks on deep learning visual classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1625–1634. IEEE
7.
Zurück zum Zitat Ding Y, Zhu G, Chen D, Qin X, Cao M, Qin Z (2022) Adversarial sample attack and defense method for encrypted traffic data. IEEE Trans Intell Transp Syst 23(10):18024–18039. IEEE Ding Y, Zhu G, Chen D, Qin X, Cao M, Qin Z (2022) Adversarial sample attack and defense method for encrypted traffic data. IEEE Trans Intell Transp Syst 23(10):18024–18039. IEEE
8.
Zurück zum Zitat Shen L, Ji S, Zhang X, Li J, Chen J, Shi J, Fang C, Yin J, Wang T (2021) Backdoor pre-trained models can transfer to all. Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, 3141–3158 Shen L, Ji S, Zhang X, Li J, Chen J, Shi J, Fang C, Yin J, Wang T (2021) Backdoor pre-trained models can transfer to all. Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, 3141–3158
9.
Zurück zum Zitat Xue M, He C, Wang J, Liu W (2021) Backdoors hidden in facial features: A novel invisible backdoor attack against face recognition systems. Peer-to-peer Netw Appl 14:1458–1474CrossRef Xue M, He C, Wang J, Liu W (2021) Backdoors hidden in facial features: A novel invisible backdoor attack against face recognition systems. Peer-to-peer Netw Appl 14:1458–1474CrossRef
10.
Zurück zum Zitat Liu K, Dolan-Gavitt B, Garg S (2018) Fine-pruning: Defending against backdooring attacks on deep neural networks. In: International Symposium on Research in Attacks, Intrusions, and Defenses, pp 273–294. Springer Liu K, Dolan-Gavitt B, Garg S (2018) Fine-pruning: Defending against backdooring attacks on deep neural networks. In: International Symposium on Research in Attacks, Intrusions, and Defenses, pp 273–294. Springer
11.
12.
Zurück zum Zitat Gao Y, Doan BG, Zhang Z, Ma S, Zhang J, Fu A, Nepal S, Kim H (2020) Backdoor attacks and countermeasures on deep learning: A comprehensive review. IEEE Open J Comput Soc 4:134–146 Gao Y, Doan BG, Zhang Z, Ma S, Zhang J, Fu A, Nepal S, Kim H (2020) Backdoor attacks and countermeasures on deep learning: A comprehensive review. IEEE Open J Comput Soc 4:134–146
13.
Zurück zum Zitat Gu T, Dolan-Gavitt B, Garg S (2017) Badnets: Identifying vulnerabilities in the machine learning model supply chain. CoRR abs/1708.06733 Gu T, Dolan-Gavitt B, Garg S (2017) Badnets: Identifying vulnerabilities in the machine learning model supply chain. CoRR abs/1708.06733
14.
Zurück zum Zitat Chen X, Liu C, Li B, Lu K, Song D (2017) Targeted backdoor attacks on deep learning systems using data poisoning. Procedia Comput Sci 192:3570–3579 Chen X, Liu C, Li B, Lu K, Song D (2017) Targeted backdoor attacks on deep learning systems using data poisoning. Procedia Comput Sci 192:3570–3579
15.
Zurück zum Zitat Chen C, Wei L, Zhang L, Peng Y, Ning J (2022) Mp-badnet+: Secure and effective backdoor attack detection and mitigation protocols among multi-participants in private dnns. Peer-to-peer Netw Appl 15(6):2457–2473CrossRef Chen C, Wei L, Zhang L, Peng Y, Ning J (2022) Mp-badnet+: Secure and effective backdoor attack detection and mitigation protocols among multi-participants in private dnns. Peer-to-peer Netw Appl 15(6):2457–2473CrossRef
16.
Zurück zum Zitat Zhang H, Gu J, Zhang Z, Du L, Zhang Y, Ren Y, Zhang J, Li H (2023) Backdoor attacks against deep reinforcement learning based traffic signal control systems. Peer-to-peer Netw Appl 16(1):466–474CrossRef Zhang H, Gu J, Zhang Z, Du L, Zhang Y, Ren Y, Zhang J, Li H (2023) Backdoor attacks against deep reinforcement learning based traffic signal control systems. Peer-to-peer Netw Appl 16(1):466–474CrossRef
17.
Zurück zum Zitat Chen B, Carvalho W, Baracaldo N, Ludwig H, Edwards B, Lee T, Molloy I, Srivastava B (2018) Detecting backdoor attacks on deep neural networks by activation clustering. Computers & Security 120:102814 Chen B, Carvalho W, Baracaldo N, Ludwig H, Edwards B, Lee T, Molloy I, Srivastava B (2018) Detecting backdoor attacks on deep neural networks by activation clustering. Computers & Security 120:102814
18.
Zurück zum Zitat Wang Y, Su Z, Zhang N, Xing R, Liu D, Luan TH, Shen X (2022) A survey on metaverse: Fundamentals, security, and privacy. IEEE Commun Surv Tutor 25(1):319–352. IEEE Wang Y, Su Z, Zhang N, Xing R, Liu D, Luan TH, Shen X (2022) A survey on metaverse: Fundamentals, security, and privacy. IEEE Commun Surv Tutor 25(1):319–352. IEEE
19.
Zurück zum Zitat Wang W, Zhu M, Zeng X al (2017) Malware traffic classification using convolutional neural network for representation learning. In: 2017 International Conference on Information Networking (ICOIN), pp 712–717. IEEE Wang W, Zhu M, Zeng X al (2017) Malware traffic classification using convolutional neural network for representation learning. In: 2017 International Conference on Information Networking (ICOIN), pp 712–717. IEEE
20.
Zurück zum Zitat Shekhawat AS, Di Troia F, Stamp M (2019) Feature analysis of encrypted malicious traffic. Expert Syst Appl 125:130–141CrossRef Shekhawat AS, Di Troia F, Stamp M (2019) Feature analysis of encrypted malicious traffic. Expert Syst Appl 125:130–141CrossRef
21.
Zurück zum Zitat Wang P, Li S, Ye F, Wang Z, Zhang M (2020) Packetcgan: Exploratory study of class imbalance for encrypted traffic classification using cgan. In: ICC 2020-2020 IEEE International Conference on Communications (ICC), pp 1–7. IEEE Wang P, Li S, Ye F, Wang Z, Zhang M (2020) Packetcgan: Exploratory study of class imbalance for encrypted traffic classification using cgan. In: ICC 2020-2020 IEEE International Conference on Communications (ICC), pp 1–7. IEEE
22.
Zurück zum Zitat Li F, Shen H, Mai J, Wang T, Dai Y, Miao X (2024) Pre-trained language model-enhanced conditional generative adversarial networks for intrusion detection. Peer-to-peer Netw Appl 17(1):227–245CrossRef Li F, Shen H, Mai J, Wang T, Dai Y, Miao X (2024) Pre-trained language model-enhanced conditional generative adversarial networks for intrusion detection. Peer-to-peer Netw Appl 17(1):227–245CrossRef
23.
Zurück zum Zitat Shahbaz R, Liu X (2019) Deep learning for encrypted traffic classification: An overview. IEEE Commun Mag 57(5):76–81. IEEE Shahbaz R, Liu X (2019) Deep learning for encrypted traffic classification: An overview. IEEE Commun Mag 57(5):76–81. IEEE
24.
Zurück zum Zitat Liu C, He L, Xiong G et al (2019) Fs-net: A flow sequence network for encrypted traffic classification. In: IEEE INFOCOM 2019-IEEE Conference On Computer Communications, pp 1171–1179. IEEE Liu C, He L, Xiong G et al (2019) Fs-net: A flow sequence network for encrypted traffic classification. In: IEEE INFOCOM 2019-IEEE Conference On Computer Communications, pp 1171–1179. IEEE
25.
Zurück zum Zitat He Y, Li W (2020) Image-based encrypted traffic classification with convolution neural networks. In: 2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC), pp 271–278. IEEE He Y, Li W (2020) Image-based encrypted traffic classification with convolution neural networks. In: 2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC), pp 271–278. IEEE
26.
Zurück zum Zitat Shen M, Zhang J, Zhu L, Xu K, Du X, Liu Y (2019) Encrypted traffic classification of decentralized applications on ethereum using feature fusion. In: Proceedings of the International Symposium on Quality of Service, pp 1–10 Shen M, Zhang J, Zhu L, Xu K, Du X, Liu Y (2019) Encrypted traffic classification of decentralized applications on ethereum using feature fusion. In: Proceedings of the International Symposium on Quality of Service, pp 1–10
27.
Zurück zum Zitat Wang B, Yao Y, Shan S, Li H, Viswanath B, Zheng H, Zhao BY (2019) Neural cleanse: Identifying and mitigating backdoor attacks in neural networks. In: 2019 IEEE Symposium on Security and Privacy (SP), pp 707–723. IEEE Wang B, Yao Y, Shan S, Li H, Viswanath B, Zheng H, Zhao BY (2019) Neural cleanse: Identifying and mitigating backdoor attacks in neural networks. In: 2019 IEEE Symposium on Security and Privacy (SP), pp 707–723. IEEE
28.
Zurück zum Zitat Li Y, Li Y, Wu B et al (2021) Invisible backdoor attack with sample-specific triggers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 16463–16472. IEEE Li Y, Li Y, Wu B et al (2021) Invisible backdoor attack with sample-specific triggers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 16463–16472. IEEE
29.
Zurück zum Zitat Liu Y, Ma X, Bailey J et al (2020) Reflection backdoor: A natural backdoor attack on deep neural networks. In: European Conference on Computer Vision, pp 182–199. Springer Liu Y, Ma X, Bailey J et al (2020) Reflection backdoor: A natural backdoor attack on deep neural networks. In: European Conference on Computer Vision, pp 182–199. Springer
30.
Zurück zum Zitat Doan K, Lao Y, Zhao W et al (2021) Lira: Learnable, imperceptible and robust backdoor attacks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 11966–11976. IEEE Doan K, Lao Y, Zhao W et al (2021) Lira: Learnable, imperceptible and robust backdoor attacks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 11966–11976. IEEE
31.
Zurück zum Zitat Draper-Gil G, Lashkari AH, Mamun MSI, Ghorbani AA (2016) Characterization of encrypted and vpn traffic using time-related. In: Proceedings of the 2nd International Conference on Information Systems Security and Privacy (ICISSP), pp 407–414 Draper-Gil G, Lashkari AH, Mamun MSI, Ghorbani AA (2016) Characterization of encrypted and vpn traffic using time-related. In: Proceedings of the 2nd International Conference on Information Systems Security and Privacy (ICISSP), pp 407–414
Metadaten
Titel
A steganographic backdoor attack scheme on encrypted traffic
verfasst von
Bing Rao
Guiqin Zhu
Qiaolong Ding
Dajiang Chen
Mingsheng Cao
Yang Cao
Feiyan Wang
Publikationsdatum
01.04.2025
Verlag
Springer US
Erschienen in
Peer-to-Peer Networking and Applications / Ausgabe 2/2025
Print ISSN: 1936-6442
Elektronische ISSN: 1936-6450
DOI
https://doi.org/10.1007/s12083-024-01893-7