Network Attacks Detection Methods Based on Deep Learning Techniques: A Survey

Table 4

Quantitative evaluation of listed attack detection methods using different deep learning structures, where ID, MD, and TI represent network intrusion detection, malware detection, and traffic identification, respectively.

DL	Method	Usage	Dataset	ACC (%)	PR (%)	FPR (%)	FS
Convolutional AE	Yu et al. [26]	ID	CTU-UNB	—	98.44	—	0.980
Sparse AE	Javaid et al. [29]	ID	NSL-KDD	98.30	—	—	0.990
AE	Pamartzivanos et al. [30]	ID	KDDCup 99	77.99	80.00	—	—
SAE	Farahnakian and Heikkonen [28]	ID	KDDCup 99	94.71	94.53	0.42	—
AE	Shone et al. [17]	ID	NSL-KDD	89.22	92.97	10.78	0.910
Sparse AE	Shone et al. [17]	ID	KDDCup 99	97.85	99.99	2.15	0.980
AE	Aygun and Yavuz [64]	ID	NSL-KDD	93.62	91.39	—	0.938
Denoising AE	Aygun and Yavuz [64]	ID	NSL-KDD	94.35	94.26	—	0.940
Sparse AE	Gharic et al. [65]	ID	NSL-KDD	96.45	95.56	—	0.965
AE	Yousefi-Azar et al. [27]	ID, MD	NSL-KDD	83.34	—	—	—
DBN	Gao et al. [31]	ID	KDDCup 99	93.49	92.33	0.76	—
DBN	Ding et al. [32]	MD	Netflow	96.10	—	—	—
DBN	Qu et al. [66]	ID	NSL-KDD	95.25	—	—	—
DBN	Tan et al. [33]	ID	Netflow	97.60	—	0.90	—
DBN	Alom et al. [34]	ID	40% NSL-KDD	97.50	—	—	—
DBN	Zhao et al. [35]	ID	KDDCup 99	99.14	93.25	0.62	—
DBN	Alrawashdeh and Purdy [36]	ID	10% KDDCup 99	97.90	97.81	2.10	0.975
DNN	Tang et al. [40]	ID	NSL-KDD	91.70	83.00	—	—
DNN	Vinayakumar et al. [18]	ID, MD	KDDCup 99	93.00	99.00	0.95
DNN	Wang et al. [42]	ID	KDDCup 99	95.45	—	—	—
CNN	Kolosnjaji et al. [43]	MD	Netflow	—	93.00	—	0.920
CNN	Saxe and Berlin [19]	MD	Netflow	92.00	—	0.10	—
CNN	Wang et al. [45]	ID	ISCX	—	97.30	—	0.960
CNN	Wang et al. [47]	TI	Netflow	99.41	—	—	—
CNN	Tang et al. [49]	ID	NS2 simulation	97.1	—	—	—
CNN	Yang and Wang [48]	ID	KDDCup 99	95.36	95.55	0.76	0.930
LSTM	Staudemyer [50]	ID	10% KDDCup 99	93.85	—	1.62	—
RNN	Krishnan and Raajan [51]	ID	KDDCup 99	77.55	84.60	—	0.730
RNN	Yin et al. [52]	ID	NSL-KDD	83.28	—	—	—
LSTM	Kim et al. [54]	ID	10% KDDCup 99	96.93	98.80	10.00	—
LSTM	Le et al. [55]	ID	KDDCup 99	97.54	98.95	9.98	—
LSTM	Kim et al. [53]	ID	KDDCup 99	99.80	—	5.50	—
GRU	Agarap [56]	ID	Netflow	84.15	—	—	—
Ensemble	Ludwig [58]	ID	NSL-KDD	92.50	93.00	0.92	—
AE, DBN	Li et al. [57]	ID	KDDCup 99	92.10	—	1.58	—
DCNN	Naseer et al. [67]	ID	NSL-KDD	85.00	—	—	0.980
PL-CNN	Liu et al. [60]	ID	DARPA1998	99.36	90.56	—	0.910
PL-RNN	Liu et al. [60]	ID	DARPA1998	99.98	99.98	—	0.990