AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields
As Neural Radiance Fields (NeRFs) have emerged as a powerful tool for 3D scene representation and novel view synthesis, protecting their intellectual property (IP) from unauthorized use is becoming increasingly crucial. In this work, we aim to protect the IP of NeRFs by injecting adversarial perturbations that disrupt their unauthorized applications. However, perturbing the 3D geometry of NeRFs can easily deform the underlying scene structure and thus substantially degrade the rendering quality, which has led existing attempts to avoid geometric perturbations or restrict them to explicit spaces like meshes. To overcome this limitation, we introduce a learnable sensitivity to quantify the spatially varying impact of geometric perturbations on rendering quality. Building upon this, we propose AegisRF, a novel framework that consists of a Perturbation Field, which injects adversarial perturbations into the pre-rendering outputs (color and volume density) of NeRF models to fool an unauthorized downstream target model, and a Sensitivity Field, which learns the sensitivity to adaptively constrain geometric perturbations, preserving rendering quality while disrupting unauthorized use. Our experimental evaluations demonstrate the generalized applicability of AegisRF across diverse downstream tasks and modalities, including multi-view image classification and voxel-based 3D localization, while maintaining high visual fidelity. Codes are available at https://github.com/wkim97/AegisRF.
Code (0)
등록된 구현이 없습니다.
Tasks
Novel View SynthesisImage ClassificationSimilar Papers 제목 키워드 기반
Investigating Vulnerabilities of Deep Neural Policies
Reinforcement learning policies based on deep neural networks are vulnerable to imperceptible adversarial perturbations to their inputs, in much the same way as neural network image classifiers. Recent work has proposed …
Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)SensitivityNon-Singular Adversarial Robustness of Neural Networks
Adversarial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. While being critical, we argue that solving this singular issue alone fails to provid…
Adversarial RobustnessSensitivityAttention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
In recent years, Vision-Language-Action (VLA) models in embodied intelligence have developed rapidly. However, existing adversarial attack methods require costly end-to-end training and often generate noticeable perturba…
Adversarial AttackEvaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off
Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturba…
Adversarial Robustnessimage-classificationImage ClassificationSemantic Segmentation+1Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition
Due to the development of machine learning and speech processing, speech emotion recognition has been a popular research topic in recent years. However, the speech data cannot be protected when it is uploaded and process…
Emotion RecognitionFederated LearningSpeech Emotion Recognition