SmartBox: Benchmarking Adversarial Detection and Mitigation Algorithms for Face Recognition
Citations
353 citations
98 citations
Cites methods from "SmartBox: Benchmarking Adversarial ..."
...Recently, Goel et al. (2018) have prepared the SmartBox toolbox containing several existing adversarial generation, detection, and mitigation algorithms....
[...]
63 citations
Cites background from "SmartBox: Benchmarking Adversarial ..."
...However, the noisy structure of the perturbation makes these attacks vulnerable against conventional defense methods such as quantizing [18], smoothing [6] or training on adversarial examples [30]....
[...]
54 citations
Cites background from "SmartBox: Benchmarking Adversarial ..."
...[10] have developed a toolbox containing various algorithm corresponds to adversarial generation, detection, and mitigation....
[...]
53 citations
Cites background or methods from "SmartBox: Benchmarking Adversarial ..."
...Further, Goel et al. (2018) developed the first benchmark toolbox of algorithms for adversarial generation, detection, and mitigation for face recognition....
[...]
...t the attacks performed using image-agnostic perturbations (i.e., one noise across multiple images) can be detected using a computationally efficient algorithm based on the data distribution. Further, Goel et al. (2018) developed the first benchmark toolbox of algorithms for adversarial generation, detection, and mitigation for face recognition. Recently, Goel et al. (2019) presented one of the best security mechanis...
[...]
References
2,130 citations
2,081 citations
"SmartBox: Benchmarking Adversarial ..." refers background in this paper
...While whitebox attacks such as ElasticNet (EAD) [6], DeepFool [28], L2 [5], Fast Gradient Sign Method (FGSM) [15], Projective Gradient Descent (PGD) [26], and MI-FGSM [10] have complete access and information about the trained network, blackbox attacks such as one pixel attack [32] and universal perturbations [27]...
[...]
1,908 citations
"SmartBox: Benchmarking Adversarial ..." refers background in this paper
...While whitebox attacks such as ElasticNet (EAD) [6], DeepFool [28], L2 [5], Fast Gradient Sign Method (FGSM) [15], Projective Gradient Descent (PGD) [26], and MI-FGSM [10] have complete access and information about the trained network, blackbox attacks such as one pixel attack [32] and universal perturbations [27] have no information about the trained Deep Neural Network (DNN)....
[...]
...While whitebox attacks such as ElasticNet (EAD) [6], DeepFool [28], L2 [5], Fast Gradient Sign Method (FGSM) [15], Projective Gradient Descent (PGD) [26], and MI-FGSM [10] have complete access and information about the trained network, blackbox attacks such as one pixel attack [32] and universal perturbations [27]...
[...]
1,703 citations
1,702 citations
"SmartBox: Benchmarking Adversarial ..." refers background in this paper
...While whitebox attacks such as ElasticNet (EAD) [6], DeepFool [28], L2 [5], Fast Gradient Sign Method (FGSM) [15], Projective Gradient Descent (PGD) [26], and MI-FGSM [10] have complete access and information about the trained network, blackbox attacks such as one pixel attack [32] and universal perturbations [27]...
[...]