Papers › Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces
Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces
Ayberk Aydın, Alptekin Temizel
Deep neural networks are known to be vulnerable to adversarial perturbations. The amount of these perturbations are generally quantified using Lₚ metrics, such as L₀, L₂ and L_∞. However, even when the measured perturbations are small, they tend to be noticeable by human observers since Lₚ distance metrics are not representative of human perception. On the other hand, humans are less sensitive to changes in colorspace. In addition, pixel shifts in a constrained neighborhood are hard to notice. Motivated by these observations, we propose a method that creates adversarial examples by applying spatial transformations, which creates adversarial examples by changing the pixel locations independently to chrominance channels of perceptual colorspaces such as YC_bCᵣ and CIELAB, instead of making an additive perturbation or manipulating pixel values directly. In a targeted white-box attack setting, the proposed method is able to obtain competitive fooling rates with very high confidence. The experimental evaluations show that the proposed method has favorable results in terms of approximate perceptual distance between benign and adversarially generated images. The source code is publicly available at https://github.com/ayberkydn/stadv-torch
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections