Cyber security meets artificial intelligence: a survey Review First Online: 10 January 2019 Abstract
There is a wide range of interdisciplinary intersections between cyber security and artificial intelligence (AI). On one hand, AI technologies, such as deep learning, can be introduced into cyber security to construct smart models for implementing malware classification and intrusion detection and threating intelligence sensing. On the other hand, AI models will face various cyber threats, which will disturb their sample, learning, and decisions. Thus, AI models need specific cyber security defense and protection technologies to combat adversarial machine learning, preserve privacy in machine learning, secure federated learning, etc. Based on the above two aspects, we review the intersection of AI and cyber security. First, we summarize existing research efforts in terms of combating cyber attacks using AI, including adopting traditional machine learning methods and existing deep learning solutions. Then, we analyze the counterattacks from which AI itself may suffer, dissect their characteristics, and classify the corresponding defense methods. Finally, from the aspects of constructing encrypted neural network and realizing a secure federated deep learning, we expatiate the existing research on how to build a secure AI system.
Key words Cyber security Artificial intelligence (AI) Attack detection Defensive techniques
Project supported by the National Natural Science Foundation of China (Nos. 61431008 and 61571300)
Abeshu A, Chilamkurti N, 2018. Deep learning: the frontier for distributed attack detection in fog–to–things computing.
IEEE Commun Mag
https://doi.org/10.1109/MCOM.2018.1700332 CrossRef Google Scholar
Akhtar N, Mian A, 2018. Threat of adversarial attacks on deep learning in computer vision: a survey.
https://doi.org/10.1109/ACCESS.2018.2807385 CrossRef Google Scholar
Akhtar N, Liu J, Mian A, 2018. Defense against universal adversarial perturbations. IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.3389–3398.
https://doi.org/10.1109/CVPR.2018.00357 Google Scholar
Arulkumaran K, Deisenroth MP, Brundage M, et al., 2017. Deep reinforcement learning: a brief survey.
IEEE Signal Process Mag
https://doi.org/10.1109/MSP.2017.2743240 CrossRef Google Scholar
Aygün RC, Yavuz AG, 2017. A stochastic data discrimination based autoencoder approach for network anomaly detection. Proc 5th Signal Processing and Communications Applications Conf, p.1–4.
https://doi.org/10.1109/SIU.2017.7960410 CrossRef Google Scholar
Bonawitz K, Ivanov V, Kreuter B, et al., 2017. Practical secure aggregation for privacy–preserving machine learning. Proc ACM SIGSAC Conf on Computer and Communications Security, p.1175–1191.
https://doi.org/10.1145/3133956.3133982 CrossRef Google Scholar
Bost R, Popa RA, Tu S, et al., 2015. Machine learning classification over encrypted data. Network and Distributed System Security Symp, p.331–364.
https://doi.org/10.14722/ndss.2015.23241 CrossRef Google Scholar
Chowdhury MMU, Hammond F, Konowicz G, et al., 2017. A few–shot deep learning approach for improved intrusion detection. Proc 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conf, p.456–462.
https://doi.org/10.1109/UEMCON.2017.8249084 CrossRef Google Scholar
Cisse M, Adi Y, Neverova N, et al., 2017. Houdini: fooling deep structured prediction models.
https://doi.org/arxiv.org/abs/1707.05373 Google Scholar
Cubuk ED, Zoph B, Schoenholz SS, et al., 2017. Intriguing properties of adversarial examples.
https://doi.org/arxiv.org/abs/1711.02846 Google Scholar
Dada EG, 2017. A hybridized SVM–kNN–pdAPSO approach to intrusion detection system. Faculty Seminar Series, p.1–8.
Deng L, Yu D, 2014. Deep learning: methods and applications.
Found Trend Sig Process
, 7(3–4): 197–387.
https://doi.org/10.1561/2000000039 MathSciNet CrossRef zbMATH Google Scholar
Feinman R, Curtin RR, Shintre S, et al., 2017. Detecting adversarial samples from artifacts.
https://doi.org/arxiv.org/abs/1703.00410 Google Scholar
Gao W, Morris T, Reaves B, et al., 2010. On SCADA control system command and response injection and intrusion detection. eCrime Researchers Summit, p.1–9.
https://doi.org/10.1109/ecrime.2010.5706699 Google Scholar
Gebhart T, Schrater P, 2017. Adversary detection in neural networks via persistent homology.
https://doi.org/arxiv.org/abs/1711.10056 Google Scholar
Golovko VA, 2017. Deep learning: an overview and main paradigms.
Opt Memory Neur Netw
https://doi.org/10.3103/S1060992X16040081 CrossRef Google Scholar
Goodfellow IJ, Pouget–Abadie J, Mirza M, et al., 2014. Generative adversarial networks.
https://doi.org/arxiv.org/abs/1406.2661 Google Scholar
Goodfellow IJ, Shlens J, Szegedy C, 2015. Explaining and harnessing adversarial examples.
https://doi.org/arxiv.org/abs/1412.6572 Google Scholar
Gu SX, Rigazio L, 2015. Towards deep neural network architectures robust to adversarial examples.
https://doi.org/arxiv.org/abs/1412.5068 Google Scholar
Guan ZT, Li J, Wu LF, et al., 2017. Achieving efficient and secure data acquisition for cloud–supported Internet of Things in smart grid.
IEEE Internet Things J
, 4(6): 1934–1944.
https://doi.org/10.1109/JIOT.2017.2690522 CrossRef Google Scholar
Hatcher WG, Yu W, 2018. A survey of deep learning: platforms, applications and emerging research trends.
https://doi.org/10.1109/ACCESS.2018.2830661 CrossRef Google Scholar
He W, Wei J, Chen XY, et al., 2017. Adversarial example defenses: ensembles of weak defenses are not strong.
https://doi.org/arxiv.org/abs/1706.04701 Google Scholar
Kokila RT, Selvi ST, Govindarajan K, 2014. DDoS detection and analysis in SDN–based environment using support vector machine classifier. Proc 6th Int Conf on Advanced Computing, p.205–210.
https://doi.org/10.1109/ICoAC.2014.7229711 CrossRef Google Scholar
Korczak J, Hernes M, 2017. Deep learning for financial time series forecasting in a–trader system. Proc Federated Conf on Computer Science and Information Systems, p.905–912.
https://doi.org/10.15439/2017F449 CrossRef Google Scholar
Krotov D, Hopfield J, 2018. Dense associative memory is robust to adversarial inputs. Neur Comput, 30(12): 3151–3167.
https://doi.org/10.1162/neco_a_01143 CrossRef Google Scholar
LeCun Y, Bengio Y, Hinton G, 2015. Deep learning.
https://doi.org/10.1038/Nature14539 CrossRef Google Scholar
Lee H, Han S, Lee J, 2017. Generative adversarial trainer: defense to adversarial perturbations with GAN.
https://doi.org/arxiv.org/abs/1705.03387 Google Scholar
Li GL, Wu J, Li JH, et al., 2018. Service popularity–based smart resources partitioning for fog computing–enabled industrial Internet of Things.
IEEE Trans Ind Inform
https://doi.org/10.1109/TII.2018.2845844 CrossRef Google Scholar
Li LZ, Ota K, Dong MX, 2018a. Deep learning for smart industry: efficient manufacture inspection system with fog computing.
IEEE Trans Ind Inform
https://doi.org/10.1109/TII.2018.2842821 CrossRef Google Scholar
Li LZ, Ota K, Dong MX, 2018b. DeepNFV: a light–weight framework for intelligent edge network functions virtualization. IEEE Netw, in press.
https://doi.org/10.1109/MNET.2018.1700394 Google Scholar
Liang B, Li HC, Su MQ, et al., 2017. Detecting adversarial image examples in deep networks with adaptive noise reduction.
https://doi.org/arxiv.org/abs/1705.08378 Google Scholar
Loukas G, Vuong T, Heartfield R, et al, 2018. Cloud–based cyber–physical intrusion detection for vehicles using deep learning.
https://doi.org/10.1109/ACCESS.2017.2782159 CrossRef Google Scholar
Luo Y, Boix X, Roig G, et al., 2015. Foveation–based mechanisms alleviate adversarial examples.
https://doi.org/arxiv.org/abs/1511.06292 Google Scholar
Lyu C, Huang KZ, Liang HN, 2015. A unified gradient regularization family for adversarial examples. IEEE Int Conf on Data Mining, p.301–309.
https://doi.org/10.1109/ICDM.2015.84 CrossRef Google Scholar
Manning CD, Surdeanu M, Bauer J, et al., 2014. The Stanford CoreNLP natural language processing toolkit. Proc 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, p.55–60.
CrossRef Google Scholar
McMahan HB, Moore E, Ramage D, et al., 2016. Communication–efficient learning of deep networks from decentralized data.
https://doi.org/arxiv.org/abs/1602.05629 Google Scholar
Meng DY, Chen H, 2017. MagNet: a two–pronged defense against adversarial examples. Proc ACM Conf on Computer and Communications Security, p.135–147.
https://doi.org/10.1145/3133956.3134057 CrossRef Google Scholar
Meng WZ, Li WJ, Kwok LF, 2015. Design of intelligent KNNbased alarm filter using knowledge–based alert verification in intrusion detection.
Secur Commun Netw
, 8(18): 3883–3895.
https://doi.org/10.1002/sec.1307 CrossRef Google Scholar
Meng X, Shan Z, Liu FD, et al., 2017. MCSMGS: malware classification model based on deep learning. Int Conf on Cyber–Enabled Distributed Computing and Knowledge Discovery, p.272–275.
https://doi.org/10.1109/CyberC.2017.21 Google Scholar
Mnih V, Kavukcuoglu K, Silver D, et al., 2015. Human–level control through deep reinforcement learning.
https://doi.org/10.1038/nature14236 CrossRef Google Scholar
Moon D, Im H, Kim I, et al., 2017. DTB–IDS: an intrusion detection system based on decision tree using behavior analysis for preventing APT attacks.
https://doi.org/10.1007/s11227-015-1604-8 CrossRef Google Scholar
Moosavi–Dezfooli SM, Fawzi A, Frossard P, 2016. DeepFool: a simple and accurate method to fool deep neural networks. IEEE Conf on Computer Vision and Pattern Recognition, p.2574–2582.
https://doi.org/10.1109/CVPR.2016.282 Google Scholar
Moosavi–Dezfooli SM, Fawzi A, Fawzi O, et al., 2017. Universal adversarial perturbations. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.86–94.
https://doi.org/10.1109/CVPR.2017.17 CrossRef Google Scholar
Mopuri KR, Garg U, Babu RV, 2017. Fast feature fool: a data independent approach to universal adversarial perturbations.
https://doi.org/arxiv.org/abs/1707.05572 Google Scholar
Nayebi A, Ganguli S, 2017. Biologically inspired protection of deep networks from adversarial attacks.
https://doi.org/arxiv.org/abs/1703.09202 Google Scholar
Olalere M, Abdullah MT, Mahmod R, et al., 2016. Identification and evaluation of discriminative lexical features of malware URL for real–time classification. Int Conf on Computer and Communication Engineering, p.90–95.
https://doi.org/10.1109/ICCCE.2016.31 CrossRef Google Scholar
Ota K, Dao MS, Mezaris V, et al., 2017. Deep learning for mobile multimedia: a survey. ACM Trans Multim Comput Commun Appl, 13(3S), Article 34.
https://doi.org/10.1145/3092831 CrossRef Google Scholar
Papernot N, McDaniel P, Jha S, et al., 2016. The limitations of deep learning in adversarial settings. IEEE European Symp on Security and Privacy, p.372–387.
https://doi.org/10.1109/EuroSP.2016.36 CrossRef Google Scholar
Phong LT, Aono Y, Hayashi T, et al., 2018. Privacypreserving deep learning via additively homomorphic encryption.
IEEE Trans Inform Forens Secur
, 13(5): 1333–1345.
https://doi.org/10.1109/TIFS.2017.2787987 CrossRef Google Scholar
Ren SQ, He KM, Girshick R, et al., 2017. Faster R–CNN: towards real–time object detection with region proposal networks.
IEEE Trans Patt Anal Mach Intell
, 39(6): 1137–1149.
https://doi.org/10.1109/TPAMI.2016.2577031 CrossRef Google Scholar
Ross AS, Doshi–Velez F, 2017. Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients.
https://doi.org/arxiv.org/abs/1711.09404 Google Scholar
Sabour S, Cao YS, Faghri F, et al., 2015. Adversarial manipulation of deep representations.
https://doi.org/arxiv.org/abs/1511.05122 Google Scholar
Shahid N, Aleem SA, Naqvi IH, et al., 2012. Support vector machine based fault detection & classification in smart grids. IEEE Globecom Workshops, p.1526–1531.
https://doi.org/10.1109/GLOCOMW.2012.6477812 CrossRef Google Scholar
Shokri R, Shmatikov V, 2015. Privacy–preserving deep learning. Proc 53rd Annual Allerton Conf on Communication, Control, and Computing, p.1310–1321.
https://doi.org/10.1109/ALLERTON.2015.7447103 Google Scholar
Syarif AR, Gata W, 2017. Intrusion detection system using hybrid binary PSO and K–nearest neighborhood algorithm. 11th Int Conf on Information & Communication Technology and System, p.181–186.
https://doi.org/10.1109/ICTS.2017.8265667 CrossRef Google Scholar
Vinayakumar R, Soman KP, Poornachandran P, et al., 2018. Detecting Android malware using long short–term memory (LSTM).
J Int Fuzzy Syst
Vollmer T, Manic M, 2009. Computationally efficient neural network intrusion security awareness. Proc 2nd Int Symp on Resilient Control Systems, p.25–30.
https://doi.org/10.1109/ISRCS.2009.5251357 CrossRef Google Scholar
Vuong TP, Loukas G, Gan D, et al., 2015. Decision tree–based detection of denial of service and command injection attacks on robotic vehicles. IEEE Int Workshop on Information Forensics and Security, p.1–6.
https://doi.org/10.1109/WIFS.2015.7368559 CrossRef Google Scholar
Wu J, Dong MX, Ota K, et al., 2018. Big data analysis–based secure cluster management for optimized control plane in software–defined networks.
IEEE Trans Netw Serv Manag
https://doi.org/10.1109/TNSM.2018.2799000 CrossRef Google Scholar
Xie CH, Wang JY, Zhang ZS, et al., 2017. Adversarial examples for semantic segmentation and object detection. IEEE Int Conf on Computer Vision, p.1378–1387.
https://doi.org/10.1109/ICCV.2017.153 CrossRef Google Scholar
Xin Y, Kong LS, Liu Z, et al., 2018. Machine learning and deep learning methods for cybersecurity.
https://doi.org/10.1109/ACCESS.2018.2836950 CrossRef Google Scholar
Xu WL, Evans D, Qi YJ, 2017. Feature squeezing mitigates and detects Carlini/Wagner adversarial examples.
https://doi.org/arxiv.org/abs/1705.10686 Google Scholar
Yuan XY, 2017. PhD forum: deep learning–based real–time malware detection with multi–stage analysis. IEEE Int Conf on Smart Computing, p.1–2.
https://doi.org/10.1109/SMARTCOMP.2017.7946997 Google Scholar
Zhao GZ, Zhang CX, Zheng LJ, 2017. Intrusion detection using deep belief network and probabilistic neural network. IEEE Int Conf on Computational Science and Engineering and IEEE Int Conf on Embedded and Ubiquitous Computing, p.639–642.
https://doi.org/10.1109/CSE-EUC.2017.119 CrossRef Google Scholar
Zhu DL, Jin H, Yang Y, et al., 2017. DeepFlow: deep learning–based malware detection by mining Android application for abnormal usage of sensitive data. IEEE Symp on Computers and Communications, p.438–443.
https://doi.org/10.1109/ISCC.2017.8024568 Google Scholar
Zolotukhin M, Hämäläinen T, Kokkonen T, et al., 2016. Increasing web service availability by detecting application–layer DDoS attacks in encrypted traffic. Proc 23rd Int Conf on Telecommunications, p.1–6.
https://doi.org/10.1109/ICT.2016.7500408 Google Scholar Copyright information
© Editorial Office of Journal of Zhejiang University Science and Springer-Verlag GmbH Germany, part of Springer Nature 2018