DeepAI AI Chat
Log In Sign Up

Generating Semantic Adversarial Examples with Differentiable Rendering

by   Lakshya Jain, et al.
University of Wisconsin-Madison
berkeley college

Machine learning (ML) algorithms, especially deep neural networks, have demonstrated success in several domains. However, several types of attacks have raised concerns about deploying ML in safety-critical domains, such as autonomous driving and security. An attacker perturbs a data point slightly in the concrete feature space (e.g., pixel space) and causes the ML algorithm to produce incorrect output (e.g. a perturbed stop sign is classified as a yield sign). These perturbed data points are called adversarial examples, and there are numerous algorithms in the literature for constructing adversarial examples and defending against them. In this paper we explore semantic adversarial examples (SAEs) where an attacker creates perturbations in the semantic space representing the environment that produces input for the ML model. For example, an attacker can change the background of the image to be cloudier to cause misclassification. We present an algorithm for constructing SAEs that uses recent advances in differential rendering and inverse graphics.


On the (Statistical) Detection of Adversarial Examples

Machine Learning (ML) models are applied in a variety of tasks such as n...

Adversarial Vulnerability Bounds for Gaussian Process Classification

Machine learning (ML) classification is increasingly used in safety-crit...

Semantic Adversarial Deep Learning

Fueled by massive amounts of data, models produced by machine-learning (...

Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effect

Physical adversarial examples for camera-based computer vision have so f...

Adv3D: Generating 3D Adversarial Examples in Driving Scenarios with NeRF

Deep neural networks (DNNs) have been proven extremely susceptible to ad...

On Need for Topology-Aware Generative Models for Manifold-Based Defenses

ML algorithms or models, especially deep neural networks (DNNs), have sh...

Machine Learning needs its own Randomness Standard: Randomised Smoothing and PRNG-based attacks

Randomness supports many critical functions in the field of machine lear...