Synthesizing Robust Adversarial Examples
Standard methods for generating adversarial examples for neural networks do not consistently fool neural network classifiers in the physical world due to a combination of viewpoint shifts, camera noise, and other natural transformations, limiting their relevance to real-world systems. We demonstrate the existence of robust 3D adversarial objects, and we present the first algorithm for synthesizing examples that are adversarial over a chosen distribution of transformations. We synthesize two-dimensional adversarial images that are robust to noise, distortion, and affine transformation. We apply our algorithm to complex three-dimensional objects, using 3D-printing to manufacture the first physical adversarial objects. Our results demonstrate the existence of 3D adversarial objects in the physical world.
Code (3)
Similar Papers 제목 키워드 기반
Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models
Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unres…
Objectobject-detectionObject DetectionAssessing Robustness via Score-Based Adversarial Image Generation
Most adversarial attacks and defenses focus on perturbations within small $\ell_p$-norm constraints. However, $\ell_p$ threat models cannot capture all relevant semantic-preserving perturbations, and hence, the scope of …
Image GenerationDASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such norm-bounded examples often fail to align well with human perception, and o…
GenAttack: Practical Black-box Attacks with Gradient-Free Optimization
Deep neural networks are vulnerable to adversarial examples, even in the black-box setting, where the attacker is restricted solely to query access. Existing black-box approaches to generating adversarial examples typica…
Adversarial AttackAdversarial RobustnessEvolutionary AlgorithmsAdversarial Learning of Semantic Relevance in Text to Image Synthesis
We describe a new approach that improves the training of generative adversarial nets (GANs) for synthesizing diverse images from a text input. Our approach is based on the conditional version of GANs and expands on previ…
DiversityImage GenerationMS-SSIMSSIM