(a) fooling adversarial images taken from Nguyen et al., 2015 that do not look like any familiar object. The two images on the left (labelled ‘Electric guitar’ and ‘Robin’) have been generated using …
Images are generated using an evolutionary algorithm either using the direct or indirect encoding and generated to fool a network trained on either ImageNet or MNIST.
The inset depicts a single trial in which participants were shown three fooling adversarial images and naturalistic examples from the target category. Their task was to choose the adversarial image …
(a) Examples of images used in the experiment - for all the stimuli see Appendix 2—figures 4 and 5, (b) average levels of agreement between participants and DCNNs under the random and competitive …
The red line represents the mean, the blue line represents the median, and the black reference line represents chance agreement. The inset contains a histogram of agreement levels across the 48 …
Each row contains the adversarial image, the DCNN label for that image, the top eight participant responses. Shaded cells contain the DCNN choice, when not ranked in the top 8, it is shown at the …
Each histogram contains the adversarial stimuli and shows the percentage of responses per each choice (y-axis). The choice labels (x-axis) are ordered the same way as in Appendix 1—figures 2 and 3 …
Continued.
Continued.
Average agreement levels for each category in each condition with 95% CI are presented in (a) with the black line referring to chance agreement. The best case stimuli are presented in (b), these …
Each bar shows the agreement level for a particular image, that is, the percentage of participants that agreed with DCNN classification for that image. Each sub-figure also shows the images that …
Exp. | Test type | Mean agreement | Chance |
---|---|---|---|
1 | Fooling 2AFC N15 | 74.18% (35.61/48 images) | 50% |
2 | Fooling 2AFC N15 | 61.59% (29.56/48 images) | 50% |
3a | Fooling 48AFC N15 | 10.12% (4.86/48 images) | 2.08% |
3b | Fooling 48AFC N15 | 9.96% (4.78/48 images) | 2.08% |
4 | TV-static 8AFC N15 | 28.97% (2.32/8 images) | 12.5% |
5 | Digits 9AFC P16 | 16% (1.44/9 images) | 11.11% |
6 | Naturalistic 2AFC K18 | 73.49% (7.3/10 images) | 50% |
7 | 3D Objects 2AFC A17 | 59.55% (31.56/53 images) | 50% |
* To give the readers a sense of the levels of agreement observed in these experiments, we have also computed the average number of images in each experiment where humans and DCNNs agree as well as the level of agreement expected if participants were responding at chance.
† Stimuli sources: N15 - Nguyen et al., 2015; P16 - Papernot et al., 2016; K18 - Karmon et al., 2018; A17 - Athalye et al., 2017.