pith. sign in

arxiv: 1804.05810 · v3 · pith:ANPKCIQ3new · submitted 2018-04-16 · 💻 cs.CV · cs.CR· cs.LG· stat.ML

ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector

classification 💻 cs.CV cs.CRcs.LGstat.ML
keywords imageobjectadversarialattackfasterperturbationsphysicalr-cnn
0
0 comments X
read the original abstract

Given the ability to directly manipulate image pixels in the digital input space, an adversary can easily generate imperceptible perturbations to fool a Deep Neural Network (DNN) image classifier, as demonstrated in prior work. In this work, we propose ShapeShifter, an attack that tackles the more challenging problem of crafting physical adversarial perturbations to fool image-based object detectors like Faster R-CNN. Attacking an object detector is more difficult than attacking an image classifier, as it needs to mislead the classification results in multiple bounding boxes with different scales. Extending the digital attack to the physical world adds another layer of difficulty, because it requires the perturbation to be robust enough to survive real-world distortions due to different viewing distances and angles, lighting conditions, and camera limitations. We show that the Expectation over Transformation technique, which was originally proposed to enhance the robustness of adversarial perturbations in image classification, can be successfully adapted to the object detection setting. ShapeShifter can generate adversarially perturbed stop signs that are consistently mis-detected by Faster R-CNN as other objects, posing a potential threat to autonomous vehicles and other safety-critical computer vision systems.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations

    cs.CV 2019-06 unverdicted novelty 6.0

    Adversarial perturbations disrupt DNN-based face detectors under white-box, gray-box, and black-box settings to sabotage training data for AI face synthesis.

  2. On Physical Adversarial Patches for Object Detection

    cs.CV 2019-06 unverdicted novelty 6.0

    A physical patch suppresses all object detections by YOLOv3 even for distant objects without overlapping them.

  3. Towards Adversarially Robust Object Detection

    cs.CV 2019-07 unverdicted novelty 5.0

    Develops a multi-task learning based adversarial training approach to improve robustness of object detectors to adversarial attacks, with experiments on PASCAL-VOC and MS-COCO.

  4. Physical Adversarial Attacks on AI Surveillance Systems:Detection, Tracking, and Visible--Infrared Evasion

    cs.CV 2026-04 unverdicted novelty 3.0

    The paper organizes existing physical adversarial attack literature into a surveillance-oriented taxonomy emphasizing temporal persistence, multi-modal sensing, carrier realism, and system-level objectives, concluding...