RGB-D object recognition systems improve their predictive performances by
fusing color and depth information, outperforming neural network architectures
that rely solely on colors. While RGB-D systems are expected to be more robust
to adversarial examples than RGB-only systems, they have also been proven to be
highly vulnerable. Their robustness is similar even when the adversarial
examples are generated by altering only the original images' colors. Different
works highlighted the vulnerability of RGB-D systems; however, there is a
lacking of technical explanations for this weakness. Hence, in our work, we
bridge this gap by investigating the learned deep representation of RGB-D
systems, discovering that color features make the function learned by the
network more complex and, thus, more sensitive to small perturbations. To
mitigate this problem, we propose a defense based on a detection mechanism that
makes RGB-D systems more robust against adversarial examples. We empirically
show that this defense improves the performances of RGB-D systems against
adversarial examples even when they are computed ad-hoc to circumvent this
detection mechanism, and that is also more effective than adversarial training.

RGB-D object recognition systems are vulnerable to adversarial examples, and color features contribute to this weakness, making the network more sensitive to perturbations. To address this issue, a defense mechanism is proposed, which improves the performance of RGB-D systems against adversarial examples and exceeds the effectiveness of adversarial training.