DeepAI AI Chat
Log In Sign Up

Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization

by   Avishek Joey Bose, et al.

Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image classification models, object detection pipelines have been much harder to break. In this paper, we propose a novel strategy to craft adversarial examples by solving a constrained optimization problem using an adversarial generator network. Our approach is fast and scalable, requiring only a forward pass through our trained generator network to craft an adversarial sample. Unlike in many attack strategies, we show that the same trained generator is capable of attacking new images without explicitly optimizing on them. We evaluate our attack on a trained Faster R-CNN face detector on the cropped 300-W face dataset where we manage to reduce the number of detected faces to 0.5% of all originally detected faces. In a different experiment, also on 300-W, we demonstrate the robustness of our attack to a JPEG compression based defense typical JPEG compression level of 75% reduces the effectiveness of our attack from only 0.5% of detected faces to a modest 5.0%.


Detecting AutoAttack Perturbations in the Frequency Domain

Recently, adversarial attacks on image classification networks by the Au...

Disrupting Deepfakes with an Adversarial Attack that Survives Training

The rapid progress in generative models and autoencoders has given rise ...

Perceptually Constrained Adversarial Attacks

Motivated by previous observations that the usually applied L_p norms (p...

The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks

Most state-of-the-art machine learning (ML) classification systems are v...

DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows

Despite much recent work, detecting out-of-distribution (OOD) inputs and...

Adversarial Imaging Pipelines

Adversarial attacks play an essential role in understanding deep neural ...

Printing and Scanning Attack for Image Counter Forensics

Examining the authenticity of images has become increasingly important a...