Fetching the paper…

Reading the bibliography…

2018

Physical Adversarial Examples for Object Detectors

Eykholt, Kevin, Evtimov, Ivan, Fernandes, Earlence et al.

Original
PDF
Post on X

Understand

Deep neural networks (DNNs) are vulnerable to adversarial examples-maliciously crafted inputs that cause DNNs to make incorrect predictions.

Recent work has shown that these attacks generalize to the physical domain, to create perturbations on physical objects that fool image classifiers under a variety of real-world conditions.
Such attacks pose a risk to deep learning models used in safety-critical cyber-physical systems.
In this work, we extend physical attacks to more challenging object detection models, a broader class of deep learning algorithms widely used to detect and label multiple objects within a scene.

Physical Adversarial Examples for Object Detectors · Around

Built on

Overfeat: Integrated recognition, localization and detection using convolutional networks
2013
Earlier work this paper cites.
Explaining and harnessing adversarial examples
Original
2014
Earlier work this paper cites.
Intriguing properties of neural networks
2014
Earlier work this paper cites.
Fast R-CNN
2015
Earlier work this paper cites.
Continuous control with deep reinforcement learning
Original
2015
Earlier work this paper cites.
Deepfool: a simple and accurate method to fool deep neural networks
Original
2015
Earlier work this paper cites.
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
2015
Earlier work this paper cites.
Adversarial manipulation of deep representations
Original
2015
Earlier work this paper cites.

Similar

Faster R-CNN: Towards real-time object detection with region proposal networks
Original
2015
Cited alongside, same era.
Adversarial examples in the physical world
Original
2016
Cited alongside, same era.
Ssd: Single shot multibox detector
2016
Cited alongside, same era.
The limitations of deep learning in adversarial settings
2016
Cited alongside, same era.
You only look once: Unified, real-time object detection
2016
Cited alongside, same era.
YOLO9000: better, faster, stronger
Original
2016

Then

Adversarial patch
Original
2017
Later among the works it cites.
Towards evaluating the robustness of neural networks
2017
Later among the works it cites.
Adversarial examples for generative models
Original
2017
Later among the works it cites.
NO need to worry about adversarial examples in object detection in autonomous vehicles
Original
2017
Later among the works it cites.
Adversarial examples for semantic segmentation and object detection
Original
2017
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Cited alongside, same era.

Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition

2016

Cited alongside, same era.

Synthesizing robust adversarial examples

2017

Cited alongside, same era.

Shapeshifter: Robust physical adversarial attack on faster R-CNN object detector

2018

Closest in time.

Robust physical-world attacks on machine learning models

2018

Closest in time.