Adversarial Attacks against a Satellite-borne Multispectral Cloud Detector

• URL: http://arxiv.org/abs/2112.01723v1
• Date: Fri, 3 Dec 2021 05:27:50 GMT
• Title: Adversarial Attacks against a Satellite-borne Multispectral Cloud Detector
• Authors: Andrew Du, Yee Wei Law, Michele Sasdelli, Bo Chen, Ken Clarke, Michael Brown, Tat-Jun Chin
• Abstract summary: In this paper, we highlight the vulnerability of deep learning-based cloud detection towards adversarial attacks. By optimising an adversarial pattern and superimposing it into a cloudless scene, we bias the neural network into detecting clouds in the scene. This opens up the potential of multi-objective attacks, specifically, adversarial biasing in the cloud-sensitive bands and visual camouflage in the visible bands.
• Score: 33.11869627537352
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data collected by Earth-observing (EO) satellites are often afflicted by cloud cover. Detecting the presence of clouds -- which is increasingly done using deep learning -- is crucial preprocessing in EO applications. In fact, advanced EO satellites perform deep learning-based cloud detection on board the satellites and downlink only clear-sky data to save precious bandwidth. In this paper, we highlight the vulnerability of deep learning-based cloud detection towards adversarial attacks. By optimising an adversarial pattern and superimposing it into a cloudless scene, we bias the neural network into detecting clouds in the scene. Since the input spectra of cloud detectors include the non-visible bands, we generated our attacks in the multispectral domain. This opens up the potential of multi-objective attacks, specifically, adversarial biasing in the cloud-sensitive bands and visual camouflage in the visible bands. We also investigated mitigation strategies against the adversarial attacks. We hope our work further builds awareness of the potential of adversarial attacks in the EO community.

Related papers

• Edge-Only Universal Adversarial Attacks in Distributed Learning [49.546479320670464]
  In this work, we explore the feasibility of generating universal adversarial attacks when an attacker has access to the edge part of the model only. Our approach shows that adversaries can induce effective mispredictions in the unknown cloud part by leveraging key features on the edge side. Our results on ImageNet demonstrate strong attack transferability to the unknown cloud part.
  arXiv  Detail & Related papers  (2024-11-15T11:06:24Z)
• Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detection [21.028664417133793]
  We propose to jointly tune adversarial exposure and additive perturbation for attack and constrain image close to cloudy image as Adversarial Cloud. DefenseNet can defend the proposed Adversarial Cloud in white-box setting and other attack methods in black-box setting.
  arXiv  Detail & Related papers  (2023-06-30T07:06:13Z)
• Spatial-Frequency Discriminability for Revealing Adversarial Perturbations [53.279716307171604]
  Vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. Current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. We propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition.
  arXiv  Detail & Related papers  (2023-05-18T10:18:59Z)
• Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond [85.06231315901505]
  Rain removal aims to remove rain streaks from images/videos and reduce the disruptive effects caused by rain. This paper makes the first attempt to conduct a comprehensive study on the robustness of deep learning-based rain removal methods against adversarial attacks.
  arXiv  Detail & Related papers  (2022-03-31T10:22:24Z)
• Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey [104.71816962689296]
  Unsupervised point cloud representation learning has attracted increasing attention due to the constraint in large-scale point cloud labelling. This paper provides a comprehensive review of unsupervised point cloud representation learning using deep neural networks.
  arXiv  Detail & Related papers  (2022-02-28T07:46:05Z)
• Boosting 3D Adversarial Attacks with Attacking On Frequency [6.577812580043734]
  We propose a novel point cloud attack (dubbed AOF) that pays more attention on the low-frequency component of point clouds. Experiments validate that AOF can improve the transferability significantly compared to state-of-the-art (SOTA) attacks.
  arXiv  Detail & Related papers  (2022-01-26T13:52:17Z)
• Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS [70.60975663021952]
  We study blackbox adversarial attacks on network classifiers. We argue that attacker-defender fixed points are themselves general-sum games with complex phase transitions. We show that a continual learning approach is required to study attacker-defender dynamics.
  arXiv  Detail & Related papers  (2021-11-23T23:42:16Z)
• Explainability-Aware One Point Attack for Point Cloud Neural Networks [0.0]
  This work proposes two new attack methods: opa and cta, which go in the opposite direction. We show that the popular point cloud networks can be deceived with almost 100% success rate by shifting only one point from the input instance. We also show the interesting impact of different point attribution distributions on the adversarial robustness of point cloud networks.
  arXiv  Detail & Related papers  (2021-10-08T14:29:02Z)
• CloudShield: Real-time Anomaly Detection in the Cloud [8.406912571507569]
  CloudShield is a real-time anomaly and attack detection system for cloud computing. It distinguishes between benign programs, known attacks, and zero-day attacks. It significantly reduces false alarms by up to 99.0%.
  arXiv  Detail & Related papers  (2021-08-20T03:14:18Z)
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey [22.706623721832486]
  Cloud computing providers offer the cloud-based Deep Neural Network as an out-of-the-box service. This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services. A new theory, called cloud-based ML privacy game, is extracted from the recently published literature to provide a deep understanding of state-of-the-art research.
  arXiv  Detail & Related papers  (2021-05-13T13:45:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.