mlsanityData to 7 Oct 2026

Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks

arXiv 2402.08763 ↗First posted 13 Feb 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Endeavors in indoor robotic navigation rely on the accuracy of segmentation models to identify free space in RGB images. However, deep learning models are vulnerable to adversarial attacks, posing a significant challenge to their real-world deployment. In this study, we identify vulnerabilities within the hidden layers of neural networks and introduce a practical approach to reinforce traditional adversarial training. Our method incorporates a novel distance loss function, minimizing the gap between hidden layers in clean and adversarial images. Experiments demonstrate satisfactory performance in improving the model's robustness against adversarial perturbations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 33 references that are in the map. First posted on arXiv 13 Feb 2024.

Builds on

26 of 33 references.

References · 26

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  7. 2016Pyramid Scene Parsing Networkcited by 2,472
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  9. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  10. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  11. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  12. 2017One pixel attack for fooling deep neural networkscited by 579
14 more
  1. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  2. 2017Countering Adversarial Images using Input Transformationscited by 517
  3. 2018Adversarial Logit Pairingcited by 224
  4. 2018Learning from positive and unlabeled data: a surveycited by 218
  5. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 151
  6. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  7. 2020An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Modelscited by 67
  8. 2019Deep Visual MPC-Policy Learning for Navigationcited by 54
  9. 2017NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehiclescited by 48
  10. 2018Evaluating and Understanding the Robustness of Adversarial Logit Pairingcited by 34
  11. 2018GONet: A Semi-Supervised Deep Learning Approach For Traversability Estimationcited by 28
  12. 2020Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Drivingcited by 24
  13. 2018VUNet: Dynamic Scene View Synthesis for Traversability Estimation using an RGB Cameracited by 7
  14. 2022A Survey of Traversability Estimation for Mobile Robotscited by 7

Built on by

Not cited yet.