journal article·2022-10-31Open access

An Ontological Knowledge Base of Poisoning Attacks on Deep Neural Networks

Majed Altoub, Fahad AlQurashi, Tan Yigitcanlar, Juan Corchado, Rashid Mehmood

Applied Sciences· Volume 12· Issue 21

Abstract

Deep neural networks (DNNs) have successfully delivered cutting-edge performance in several fields. With the broader deployment of DNN models on critical applications, the security of DNNs has become an active and yet nascent area. Attacks against DNNs can have catastrophic results, according to recent studies. Poisoning attacks, including backdoor attacks and Trojan attacks, are one of the growing threats against DNNs. Having a wide-angle view of these evolving threats is essential to better understand the security issues. In this regard, creating a semantic model and a knowledge graph for poisoning attacks can reveal the relationships between attacks across intricate data to enhance the security knowledge landscape. In this paper, we propose a DNN poisoning attack ontology (DNNPAO) that would enhance knowledge sharing and enable further advancements in the field. To do so, we have performed a systematic review of the relevant literature to identify the current state. We collected 28,469 papers from the IEEE, ScienceDirect, Web of Science, and Scopus databases, and from these papers, 712 research papers were screened in a rigorous process, and 55 poisoning attacks in DNNs were identified and classified. We extracted a taxonomy of the poisoning attacks as a scheme to develop DNNPAO. Subsequently, we used DNNPAO as a framework by which to create a knowledge base. Our findings open new lines of research within the field of AI security.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Adversarial Robustness in Machine Learning · Advanced Malware Detection Techniques · Digital and Cyber Forensics

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia

School of Architecture and Built Environment, Queensland University of Technology, 2 George Street, Brisbane, QLD 4000, Australia

School of Technology, Federal University of Santa Catarina, Campus Universitario, Florianopolis 88040-900, SC, Brazil

BISITE Research Group, University of Salamanca, 37007 Salamanca, Spain

Air Institute, IoT Digital Innovation Hub, 37188 Salamanca, Spain

Department of Electronics, Information and Communication, Faculty of Engineering, Osaka Institute of Technology, Osaka 535-8585, Japan

High Performance Computing Center, King Abdulaziz University, Jeddah 21589, Saudi Arabia

Funding

Deanship of Scientific Research (DSR) at the King Abdulaziz University (KAU), Jeddah, Saudi Arabia

References (100+)

Show source-provided references
1. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
2. Object Detection With Deep Learning: A Review10.1109/TNNLS.2018.2876865 ↗
3. DIESEL: A Novel Deep Learning-Based Tool for SpMV Computations and Solving Sparse Linear Equation Systems10.1007/s11227-020-03489-3 ↗
4. Aqib, M., Mehmood, R., Alzahrani, A., Katib, I., Albeshri, A., and Altowaijri, S. (2019). Rapid Transit Systems: Smarter Urban Planning Using Big Data, In-Memory Computing, Deep Learning, and GPUs. Sustainability, 11.10.3390/su11102736 ↗
5. Chapter 9—Deep Neural Networks for Natural Language Processing
6. Ahmad, I., Alqurashi, F., Abozinadah, E., and Mehmood, R. (2022). Deep Journalism and DeepJournal V1.0: A Data-Driven Deep Learning Approach to Discover Parameters for Transportation. Sustainability, 14.10.20944/preprints202203.0245.v1 ↗
7. A review and taxonomy of wind and solar energy forecasting methods based on deep learning10.1016/j.egyai.2021.100060 ↗
8. A survey on deep learning in medicine: Why, how and when?10.1016/j.inffus.2020.09.006 ↗
9. Janbi, N., Mehmood, R., Katib, I., Albeshri, A., Corchado, J.M., and Yigitcanlar, T. (2022). Imtidad: A Reference Architecture and a Case Study on Developing Distributed AI Services for Skin Disease Diagnosis over Cloud, Fog and Edge. Sensors, 22.10.3390/s22051854 ↗
10. Yigitcanlar, T., Butler, L., Windle, E., Desouza, K.C., Mehmood, R., and Corchado, J.M. (2020). Can Building “Artificially Intelligent Cities” Safeguard Humanity from Natural Disasters, Pandemics, and Other Catastrophes? An Urban Scholar’s Perspective. Sensors, 20.10.3390/s20102988 ↗
11. Alotaibi, H., Alsolami, F., Abozinadah, E., and Mehmood, R. (2022). TAWSEEM: A Deep-Learning-Based Tool for Estimating the Number of Unknown Contributors in DNA Profiling. Electronics, 11.10.3390/electronics11040548 ↗
12. A survey on neural networks for (cyber-) security and (cyber-) security of neural networks10.1016/j.neucom.2022.06.002 ↗
13. UbeHealth: A Personalized Ubiquitous Cloud and Edge-Enabled Networked Healthcare System for Smart Cities10.1109/ACCESS.2018.2846609 ↗
14. Mohammed, T., Albeshri, A., Katib, I., and Mehmood, R. (2020). UbiPriSEQ—Deep Reinforcement Learning to Manage Privacy, Security, Energy, and QoS in 5G IoT HetNets. Appl. Sci., 10.10.3390/app10207120 ↗
15. Yigitcanlar, T., Corchado, J.M., Mehmood, R., Li, R.Y.M., Mossberger, K., and Desouza, K. (2021). Responsible urban innovation with local government artificial intelligence (Ai): A conceptual framework and research agenda. J. Open Innov. Technol. Mark. Complex., 7.10.3390/joitmc7010071 ↗
16. Yigitcanlar, T., Mehmood, R., and Corchado, J.M. (2021). Green Artificial Intelligence: Towards an Efficient, Sustainable and Equitable Technology for Smart Cities and Futures. Sustainability, 13.10.3390/su13168952 ↗
17. Adversarial Attacks and Defenses in Images, Graphs and Text: A Review10.1007/s11633-019-1211-x ↗
18. A taxonomy and survey of attacks against machine learning10.1016/j.cosrev.2019.100199 ↗
19. Dang, T.K., Truong, P.T.T., and Tran, P.T. (2020, January 25–27). Data Poisoning Attack on Deep Neural Network and Some Defense Methods. Proceedings of the 2020 International Conference on Advanced Computing and Applications (ACOMP), Quy Nhon, Vietnam.10.1109/ACOMP50827.2020.00010 ↗
20. A Taxonomy of Attacks on Federated Learning10.1109/MSEC.2020.3039941 ↗
21. Isakov, M., Gadepally, V., Gettings, K.M., and Kinsy, M.A. (2019, January 24–26). Survey of Attacks and Defenses on Edge-Deployed Neural Networks. Proceedings of the 2019 IEEE High Performance Extreme Computing Conference (HPEC), Waltham, MA, USA.10.1109/HPEC.2019.8916519 ↗
22. Chen, D., Yu, N., Zhang, Y., and Fritz, M. (2020, January 9–13). GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models. Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security (CCS ’20), Virtual.10.1145/3372297.3417238 ↗
23. Liu, Y., Mondal, A., Chakraborty, A., Zuzak, M., Jacobsen, N., Xing, D., and Srivastava, A. (2020, January 25–26). A Survey on Neural Trojans. Proceedings of the 2020 21st International Symposium on Quality Electronic Design (ISQED), Santa Clara, CA, USA.10.1109/ISQED48828.2020.9137011 ↗
24. Xu, Q., Arafin, M.T., and Qu, G. (2019, January 21–24). Security of Neural Networks from Hardware Perspective: A Survey and Beyond. Proceedings of the 26th Asia and South Pacific Design Automation Conference (ASPDAC ’21), Tokyo, Japan.
25. Machine Learning Security: Threats, Countermeasures, and Evaluations10.1109/ACCESS.2020.2987435 ↗
26. Towards Security Threats of Deep Learning Systems: A Survey10.1109/TSE.2020.3034721 ↗
27. Backdoor Attacks and Defenses for Deep Neural Networks in Outsourced Cloud Environments10.1109/MNET.011.1900577 ↗
28. Adversarial Learning Targeting Deep Neural Network Classification: A Comprehensive Review of Defenses Against Attacks10.1109/JPROC.2020.2970615 ↗
29. A systematic review of systematic review process research in software engineering10.1016/j.infsof.2013.07.010 ↗
30. Rayyan—A web and mobile app for systematic reviews10.1186/s13643-016-0384-4 ↗
31. An open source machine learning framework for efficient and transparent systematic reviews10.1038/s42256-020-00287-7 ↗
32. The protégé project: A look back and a look forward10.1145/2757001.2757003 ↗
33. (2021, May 14). Neo4j-Graph Data Platform. Available online: https://neo4j.com/.
34. Barrasa, J. (2022, March 15). Neosemantics—A Plugin That Enables the Use of RDF in Neo4j. Available online: https://github.com/neo4j-labs/neosemantics.
35. Invisible Backdoor Attacks on Deep Neural Networks Via Steganography and Regularization
36. Lee, D., Kim, H., and Ryou, J. (2020, January 19–22). Poisoning attack on show and tell model and defense using autoencoder in electric factory. Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), Busan, Korea.10.1109/BigComp48618.2020.000-9 ↗
37. Dumford, J., and Scheirer, W. (2020–1, January 28). Backdooring Convolutional Neural Networks via Targeted Weight Perturbations. Proceedings of the 2020 IEEE International Joint Conference on Biometrics (IJCB), Houston, TX, USA.10.1109/IJCB48548.2020.9304875 ↗
38. Analyzing Federated Learning through an Adversarial Lens
39. Zhou, X., Xu, M., Wu, Y., and Zheng, N. (2021). Deep Model Poisoning Attack on Federated Learning. Future Internet, 13.10.3390/fi13030073 ↗
40. Davaslioglu, K., and Sagduyu, Y.E. (2019, January 11–14). Trojan Attacks on Wireless Signal Classification with Adversarial Machine Learning. Proceedings of the 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), Newark, NJ, USA.10.1109/DySPAN.2019.8935782 ↗
41. Zhong, H., Liao, C., Squicciarini, A.C., Zhu, S., and Miller, D. (2020, January 16–18). Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation. Proceedings of the Tenth ACM Conference on Data and Application Security and Privacy (CODASPY ’20), New Orleans, LA, USA.10.1145/3374664.3375751 ↗
42. Huai, M., Sun, J., Cai, R., Yao, L., and Zhang, A. (2020, January 6–10). Malicious Attacks against Deep Reinforcement Learning Interpretations. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual.10.1145/3394486.3403089 ↗
43. One-to-N & N-to-One: Two Advanced Backdoor Attacks Against Deep Learning Models10.1109/TDSC.2020.3028448 ↗
44. Liu, K., Tan, B., Karri, R., and Garg, S. (2020, January 15). Poisoning the (Data) Well in ML-Based CAD: A Case Study of Hiding Lithographic Hotspots. Proceedings of the 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France.10.23919/DATE48585.2020.9116489 ↗
45. Practical Attacks on Deep Neural Networks by Memory Trojaning10.1109/TCAD.2020.2995347 ↗
46. Lin, J., Xu, L., Liu, Y., and Zhang, X. (2020). Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security, ACM.
47. A Backdoor Attack Against LSTM-Based Text Classification Systems10.1109/ACCESS.2019.2941376 ↗
48. Zhao, S., Ma, X., Zheng, X., Bailey, J., Chen, J., and Jiang, Y.G. (2020, January 13–19). Clean-Label Backdoor Attacks on Video Recognition Models. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01445 ↗
49. Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks10.1007/978-3-030-58607-2_11 ↗
50. Chen, J., Zhang, L., Zheng, H., and Xuan, Q. (2020). Proceedings of the ACM International Conference Proceeding Series, ACM.
51. Tan, T.J.L., and Shokri, R. (2020, January 7–11). Bypassing Backdoor Detection Algorithms in Deep Learning. Proceedings of the 2020 IEEE European Symposium on Security and Privacy (EuroS&P), Genoa, Italy.10.1109/EuroSP48549.2020.00019 ↗
52. Tang, R., Du, M., Liu, N., Yang, F., and Hu, X. (2020, January 6–10). An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual.10.1145/3394486.3403064 ↗
53. A security concern about deep learning models
54. Barni, M., Kallas, K., and Tondi, B. (2019, January 22–25). A New Backdoor Attack in CNNS by Training Set Corruption Without Label Poisoning. Proceedings of the 2019 IEEE International Conference on Image Process, Taipei, Taiwan.10.1109/ICIP.2019.8802997 ↗
55. Escaping Backdoor Attack Detection of Deep Learning10.1007/978-3-030-58201-2_29 ↗
56. Kwon, H., Roh, J., Yoon, H., and Park, K.W. (2020). Proceedings of the ACM Internet Conference Proceeding Series, ACM.
57. Invisible Poisoning: Highly Stealthy Targeted Poisoning Attack
58. Chen, J., Zheng, L., Zheng, H., Wang, X., and Ming, Z. (2021). DeepPoison: Feature Transfer Based Stealthy Poisoning Attack. arXiv.10.1109/TCSII.2021.3060896 ↗
59. Backdoors hidden in facial features: A novel invisible backdoor attack against face recognition systems10.1007/s12083-020-01031-z ↗
60. Yao, Y., Zheng, H., Li, H., and Zhao, B.Y. (2019, January 11–15). Latent backdoor attacks on deep neural networks. Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, London, UK.10.1145/3319535.3354209 ↗
61. Quiring, E., and Rieck, K. (2020, January 21–21). Backdooring and Poisoning Neural Networks with Image-Scaling Attacks. Proceedings of the 2020 IEEE Security and Privacy Workshops (SPW), San Francisco, CA, USA.10.1109/SPW50608.2020.00024 ↗
62. Bhalerao, A., Kallas, K., Tondi, B., and Barni, M. (2019, January 27–29). Luminance-based video backdoor attack against anti-spoofing rebroadcast detection. Proceedings of the 2019 IEEE 21st IInternational Workshop on Multimedia Signal Processing, Kuala Lumpur, Malaysia.10.1109/MMSP.2019.8901711 ↗
63. Costales, R., Mao, C., Norwitz, R., Kim, B., and Yang, J. (2020, January 14–19). Live Trojan Attacks on Deep Neural Networks. Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Seattle, WA, USA.10.1109/CVPRW50498.2020.00406 ↗
64. Multi-Targeted Backdoor: Indentifying Backdoor Attack for Multiple Deep Neural Networks10.1587/transinf.2019EDL8170 ↗
65. Liu, Z., Ye, J., Hu, X., Li, H., Li, X., and Hu, Y. (2020, January 5–8). Sequence Triggered Hardware Trojan in Neural Network Accelerator. Proceedings of the 2020 IEEE 38th VLSI Test Symposium, San Diego, CA, USA.10.1109/VTS48691.2020.9107582 ↗
66. Rakin, A.S., He, Z., and Fan, D. (2020, January 13–19). TBT: Targeted Neural Network Attack With Bit Trojan. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01321 ↗
67. Liu, T., Wen, W., and Jin, Y. (2018–4, January 30). SIN2: Stealth infection on neural network—A low-cost agile neural Trojan attack methodology. Proceedings of the 2018 IEEE International Symposium on Hardware Oriented Security and Trust (HOST), Washington, DC, USA.10.1109/HST.2018.8383920 ↗
68. Data Poisoning Attacks on Graph Convolutional Matrix Completion
69. Zhu, C., Ronny Huang, W., Shafahi, A., Li, H., Taylor, G., Studer, C., and Goldstein, T. (2019, January 9–15). Transferable clean-label poisoning attacks on deep neural nets. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA.
70. BadNets: Evaluating Backdooring Attacks on Deep Neural Networks10.1109/ACCESS.2019.2909068 ↗
71. A Master Key backdoor for universal impersonation attack against DNN-based face verification10.1016/j.patrec.2021.01.009 ↗
72. Clements, J., and Lao, Y. (2019, January 26–29). Hardware Trojan Design on Neural Networks. Proceedings of the 2019 IEEE International Symposium on Circuits and Systems (ISCAS), Sapporo, Japan.10.1109/ISCAS.2019.8702493 ↗
73. Muñoz-González, L., Biggio, B., Demontis, A., Paudice, A., Wongrassamee, V., Lupu, E.C., and Roli, F. (2017). Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, ACM.
74. Deep Reinforcement Learning for Partially Observable Data Poisoning Attack in Crowdsensing Systems10.1109/JIOT.2019.2962914 ↗
75. Li, W., Yu, J., Ning, X., Wang, P., Wei, Q., Wang, Y., and Yang, H. (2018, January 8–11). Hu-Fu: Hardware and Software Collaborative Attack Framework Against Neural Networks. Proceedings of the 2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), Hong Kong, China.10.1109/ISVLSI.2018.00093 ↗
76. Xu, J., Wen, Y., Yang, C., and Meng, D. (2020–1, January 29). An Approach for Poisoning Attacks Against RNN-Based Cyber Anomaly Detection. Proceedings of the 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), Guangzhou, China.10.1109/TrustCom50675.2020.00231 ↗
77. Venceslai, V., Marchisio, A., Alouani, I., Martina, M., and Shafique, M. (2020, January 19–24). NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips. Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.10.1109/IJCNN48605.2020.9207351 ↗
78. Kwon, H., Yoon, H., and Park, K.W. (2019, January 3–5). Selective Poisoning Attack on Deep Neural Network to Induce Fine-Grained Recognition Error. Proceedings of the 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), Sardinia, Italy.10.1109/AIKE.2019.00033 ↗
79. A New Facial Authentication Pitfall and Remedy in Web Services10.1109/TDSC.2021.3067794 ↗
80. Zeng, Y., Qiu, M., Niu, J., Long, Y., Xiong, J., and Liu, M. (2019, January 1–3). V-PSC: A Perturbation-Based Causative Attack Against DL Classifiers’ Supply Chain in VANET. Proceedings of the 2019 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC), New York, NY, USA.10.1109/CSE/EUC.2019.00026 ↗
81. Pan, J. (2020, January 16–19). Blackbox Trojanising of Deep Learning Models: Using Non-Intrusive Network Structure and Binary Alterations. Proceedings of the 2020 IEEE Region 10 Conference, Osaka, Japan.10.1109/TENCON50793.2020.9293933 ↗
82. Garofalo, G., Rimmer, V., hamme, T.V., Preuveneers, D., and Joosen, W. (2018, January 13–14). Fishy Faces: Crafting Adversarial Images to Poison Face Authentication. Proceedings of the 12th USENIX Workshop on Offensive Technologies (WOOT 18), Baltimore, MD, USA.
83. Chen, L., Li, N., Liang, K., and Schneider, S. (2020). Computer Security—ESORICS 2020, Springer International Publishing.10.1007/978-3-030-59013-0 ↗
84. Poisoning Machine Learning Based Wireless IDSs via Stealing Learning Model10.1007/978-3-319-94268-1_22 ↗
85. Zhang, J., Chen, J., Wu, D., Chen, B., and Yu, S. (2019, January 5–8). Poisoning Attack in Federated Learning using Generative Adversarial Nets. Proceedings of the 2019 18th IEEE International Conference on Trust, Security and Privacy in Computing And Communications/13th IEEE International Conference on Big Data Science and Engineering (TrustCom/BigDataSE), Rotorua, New Zealand.10.1109/TrustCom/BigDataSE.2019.00057 ↗
86. Lovisotto, G., Eberz, S., and Martinovic, I. (2020, January 7–11). Biometric Backdoors: A Poisoning Attack Against Unsupervised Template Updating. Proceedings of the 2020 IEEE European Symposium on Security and Privacy (EuroS&P), Genoa, Italy.10.1109/EuroSP48549.2020.00020 ↗
87. Fofanov, G.A. (July, January 29). Problems of Neural Networks Training. Proceedings of the 2018 19th International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices (EDM), Erlagol, Russia.10.1109/EDM.2018.8434935 ↗
88. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
89. Finding Structure in Time10.1207/s15516709cog1402_1 ↗
90. Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and Harnessing Adversarial Examples. arXiv.
91. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arXiv.
92. Reinforcement Learning: An Introduction10.1109/TNN.1998.712192 ↗
93. Networks of spiking neurons: The third generation of neural network models10.1016/S0893-6080(97)00011-7 ↗
94. Communication-Efficient Learning of Deep Networks from Decentralized Data
95. Ji, Y., Zhang, X., Ji, S., Luo, X., and Wang, T. (2019, January 15–19). Model-Reuse Attacks on Deep Learning Systems. Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, Toronto, ON, Canada.10.1145/3243734.3243757 ↗
96. Chen, X., Liu, C., Li, B., Lu, K., and Song, D. (2017). Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning. arXiv.
97. Liu, Y., Xie, Y., and Srivastava, A. (2017, January 5–8). Neural Trojans. Proceedings of the 2017 IEEE International Conference on Computer Design (ICCD), Boston, MA, USA.10.1109/ICCD.2017.16 ↗
98. Zou, M., Shi, Y., Wang, C., Li, F., Song, W., and Wang, Y. (2018). PoTrojan: Powerful neural-level trojan designs in deep learning models. arXiv.
99. The Apache Software Foundation (ASF) (2022, October 19). Apache JMeter. Available online: https://jmeter.apache.org.
100. Altoub, M. (2022, October 22). DNNOAO-DNN Poisoning Attacks Ontology. Available online: https://github.com/MajedCS/DNNPAO.