Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers

• URL: http://arxiv.org/abs/2012.15183v1
• Date: Wed, 30 Dec 2020 15:05:53 GMT
• Title: Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers
• Authors: Krishna Kanth Nakka and Mathieu Salzmann
• Abstract summary: We propose a framework to generate a single temporally transferable adversarial perturbation from the object template image only. This perturbation can then be added to every search image, which comes at virtually no cost, and still, successfully fool the tracker.
• Score: 81.90113217334424
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, the trackers based on Siamese networks have emerged as highly effective and efficient for visual object tracking (VOT). While these methods were shown to be vulnerable to adversarial attacks, as most deep networks for visual recognition tasks, the existing attacks for VOT trackers all require perturbing the search region of every input frame to be effective, which comes at a non-negligible cost, considering that VOT is a real-time task. In this paper, we propose a framework to generate a single temporally transferable adversarial perturbation from the object template image only. This perturbation can then be added to every search image, which comes at virtually no cost, and still, successfully fool the tracker. Our experiments evidence that our approach outperforms the state-of-the-art attacks on the standard VOT benchmarks in the untargeted scenario. Furthermore, we show that our formalism naturally extends to targeted attacks that force the tracker to follow any given trajectory by precomputing diverse directional perturbations.

Related papers

• Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks [1.7907721703063868]
  Adrial attacks in visual object tracking have significantly degraded the performance of advanced trackers. We propose an effective auxiliary pre-processing defense network, AADN, which performs defensive transformations on the input images before feeding them into the tracker.
  arXiv  Detail & Related papers  (2024-02-28T01:42:31Z)
• Pre-trained Trojan Attacks for Visual Recognition [106.13792185398863]
  Pre-trained vision models (PVMs) have become a dominant component due to their exceptional performance when fine-tuned for downstream tasks. We propose the Pre-trained Trojan attack, which embeds backdoors into a PVM, enabling attacks across various downstream vision tasks. We highlight the challenges posed by cross-task activation and shortcut connections in successful backdoor attacks.
  arXiv  Detail & Related papers  (2023-12-23T05:51:40Z)
• Efficient universal shuffle attack for visual object tracking [12.338273740874891]
  We propose an offline universal adversarial attack called Efficient Universal Shuffle Attack. It takes only one perturbation to cause the tracker malfunction on all videos. Experimental results show that EUSA can significantly reduce the performance of state-of-the-art trackers.
  arXiv  Detail & Related papers  (2022-03-14T07:48:06Z)
• Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking [15.38386172273694]
  This work proposes a novel adaptive adversarial attack approach, i.e., Ad$2$Attack, against UAV object tracking. A novel optimization function is proposed for balancing the imperceptibility and efficiency of the attack. Experiments on several well-known benchmarks and real-world conditions show the effectiveness of our attack method.
  arXiv  Detail & Related papers  (2022-03-03T05:00:32Z)
• Learning Target Candidate Association to Keep Track of What Not to Track [100.80610986625693]
  We propose to keep track of distractor objects in order to continue tracking the target. To tackle the problem of lacking ground-truth correspondences between distractor objects in visual tracking, we propose a training strategy that combines partial annotations with self-supervision. Our tracker sets a new state-of-the-art on six benchmarks, achieving an AUC score of 67.2% on LaSOT and a +6.1% absolute gain on the OxUvA long-term dataset.
  arXiv  Detail & Related papers  (2021-03-30T17:58:02Z)
• Efficient Adversarial Attacks for Visual Object Tracking [73.43180372379594]
  We present an end-to-end network FAN (Fast Attack Network) that uses a novel drift loss combined with the embedded feature loss to attack the Siamese network based trackers. Under a single GPU, FAN is efficient in the training speed and has a strong attack performance.
  arXiv  Detail & Related papers  (2020-08-01T08:47:58Z)
• Robust Tracking against Adversarial Attacks [69.59717023941126]
  We first attempt to generate adversarial examples on top of video sequences to improve the tracking robustness against adversarial attacks. We apply the proposed adversarial attack and defense approaches to state-of-the-art deep tracking algorithms.
  arXiv  Detail & Related papers  (2020-07-20T08:05:55Z)
• Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises [87.53808756910452]
  A cooling-shrinking attack method is proposed to deceive state-of-the-art SiameseRPN-based trackers. Our method has good transferability and is able to deceive other top-performance trackers such as DaSiamRPN, DaSiamRPN-UpdateNet, and DiMP.
  arXiv  Detail & Related papers  (2020-03-21T07:13:40Z)

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.