Tripod: Use Data Augmentation to Enhance Website Fingerprinting

A Survey on Deep Learning for Website Fingerprinting Attacks and Defenses

“…Similarly, for the packet timings and sizes they enforced all of application constraints for generating adversarial examples. Zhang et al [47] proposed Tripod, a novel data augmentation method for WF attacks, which applied three packet manipulations (Injecting, Removing, and Losing) on one collected traffic trace to generate several augmented traces, experimental results on ResNet-18, ResNet-34, VGG-16, VGG-19, DF, Var-CNN showed that Tripod had good universality because it had enhanced these six WF attacks and may work with more WF attacks. Chen et al [48] introduced a model-agnostic, efficient, and harmonious data augmentation (HDA) method that can improve deep WF attacks significantly, the method augmented the original training data by rotating and masking out randomly individual samples and mixing (linearly combining) sample pairs in arbitrary proportions, experimental results showed that Var-CNN with HDA achieved the best results.…”

“…Experiments showed that HDA can boost deep learning WF attack models like Var-CNN in both closed-world and open-world settings, at the absense and presence of strong defense. Tripod [47] used three manipulations of Injecting, Removing, and Losing on one collected traffic trace to generate several augmented traces, reflecting the changes or exceptions of the Internet. The Injecting manipulation introduced background traffic.…”

“…When the size of the world was significantly increased, its performance degraded significantly to 30% precision and 70% recall. [26] SDAE, CNN, LSTM DF [27] CNN GRU and ResNet [28] GRU, ResNet-50 p-FP [29] MLP, CNN Cache-based WF [30], [31] CNN, LSTM Var-CNN [32] ResNet-18 Tik-Tok [34] DF 2ch-TCN [35] CNN Realistic WF [109] CNN, LSTM Multi-session WF [39] LSTM Side-channel informationbased WF [41] CNN, LSTM BurNet [43] CNN DNNF [44] CNN GAP-WF [45] GNN Cross-trace WF [46] DF DNN with Blind adversarial training [2] DF DNN with Tripod data augmentation [47] DF, Var-CNN, ResNet-18, ResNet-34, VGG-16, VGG-19 DNN with HDA data augmentation [48] Var-CNN, ResNet-34 Microarchitecture-based WF [49] 1-D CNN BAPM [110] CNN, Self-attention FDF [52] CNN, FC, Self-attention snWF [53] CNN WFD [111] 1-D ResNets DNN with Minipatch adversarial training [54] DF DNN with Bionic data augmentation [55] Var-CNN Semi-supervised learning GANDaLF [40] GAN PAS [114] DCNN, DF, AWF Transfer learning AF [42] Domain adversarial network TLFA [51] CNN, MLP Metric-learning TF [33] Triplet networks CPWF [38] CNN CNN-BiLSTM-based Siamese networks [50] Siamese networks, CNN, LSTM Online WF [56] TF Meta-learning MBL [57] CNN…”