Search papers, labs, and topics across Lattice.
This paper introduces ColorFD, a novel black-box physical adversarial attack method for remote sensing object detection that optimizes patch positions and color parameters using Differential Evolution. By employing a target-wise fitness mechanism and two guidance strategies鈥攌ey-region localization and common-feature extraction鈥攖he method effectively navigates the high-dimensional search space to enhance attack efficacy. Experimental results demonstrate that ColorFD outperforms existing black-box patch methods and competes well with white-box approaches, showing successful transferability from digital to real-world conditions.
ColorFD achieves superior black-box physical attacks on remote sensing object detectors, outperforming traditional methods and maintaining effectiveness in real-world scenarios.
Although deep neural network-based remote sensing object detectors have achieved strong performance, they remain vulnerable to adversarial perturbations. Existing studies mainly focus on digital or white-box settings, whereas black-box physical attacks remain underexplored. These attacks are often constrained by limited physical feasibility and inefficient optimization in high-dimensional search spaces. To address these challenges, this paper proposes ColorFD, a black-box physical attack based on multiple pure-color patches. The patch positions and color parameters are jointly optimized using Differential Evolution (DE). A target-wise fitness and selection mechanism evaluates the attack state of each target and preserves target-specific improvements during evolution. Two guidance strategies further constrain the patch search space. Key-region localization identifies sensitive regions through finite-difference color probing. Common-feature extraction provides category-level spatial priors and avoids repeated localization. Although evaluated on aircraft, the formulation is not inherently restricted to this category. Experiments on YOLOv3u, YOLOv5u, and Faster R-CNN show that ColorFD outperforms the tested black-box patch method across all evaluated detectors and remains competitive with strong white-box baselines. Physical-world experiments further demonstrate that the optimized pure-color patches can be transferred from the digital domain to real imaging conditions.
