Location: WebEx Meeting link: https://uconn-cmr.webex.com/uconn-cmr/j.php?MTID=mee0bcf4f1da87ea72ff06487169d8ce9 Meeting number: 2864 425 7341 Password: ahTxJbmx674Abstract: Generalizable Neural Radiance Fields (GNeRF) are recognized as one of the most promising techniques for novel view synthesis and 3D model generation in real-world applications. However, like other generative models in computer vision, ensuring their adversarial robustness against various threat models is essential for practical use. The pioneering work in this area, NeRFool introduced a state-of-the-art attack that targets GNeRFs by manipulating source views before feature extraction to disrupt the color and density results. NeRFool effectively leveraged the unique 3D aspects of GNeRFs, achieving significant results. Building on this foundation, we propose IL2-NeRF(Iterative l2 NeRF Attack), a novel adversarial attack method that explores a new threat model(in the l2 domain) for attacking GNeRFs. We evaluated IL2-NeRF on three standard GNeRF models across three datasets, demonstrating superior performance over NeRFool, establishing IL2-NeRF as the new state-of-the-art adversarial method for GNeRFs.

Conferences & Speakers