2025/05/30 by Matthew S. Hull, Haoyang Yang, Hull, Matthew +18
Computer Science · Decision Sciences · #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #Distributed and Parallel Computing Systems #FOS: Computer and information sciences #Machine Learning (cs.LG) #Real-Time Systems Scheduling #Simulation Techniques and Applications
paper · pdf · doi:10.48550/arxiv.2506.00280
openalex publication_date 2025/05/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
With 3D Gaussian Splatting (3DGS) being increasingly used in safety-critical applications, how can an adversary manipulate the scene to cause harm? We introduce CLOAK, the first attack that leverages view-dependent Gaussian appearances - colors and textures that change with viewing angle - to embed adversarial content visible only from specific viewpoints. We further demonstrate DAGGER, a targeted adversarial attack directly perturbing 3D Gaussians without access to underlying training data, deceiving multi-stage object detectors e.g., Faster R-CNN, through established methods such as projected gradient descent. These attacks highlight underexplored vulnerabilities in 3DGS, introducing a new potential threat to robotic learning for autonomous navigation and other safety-critical 3DGS applications.