Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices

• URL: http://arxiv.org/abs/2412.02171v2
• Date: Thu, 13 Mar 2025 07:31:19 GMT
• Title: Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices
• Authors: Tianyi Wang, Zichen Wang, Cong Wang, Yuanchao Shu, Ruilong Deng, Peng Cheng, Jiming Chen,
• Abstract summary: A new class of latency attacks are reported recently targeting the real-time processing capability of object detectors.<n>We take an initial attempt to defend against this attack via background-attentive adversarial training.<n>Experiments demonstrate the defense effectiveness of restoring real-time processing capability from $13$ FPS to $43$ FPS.
• Score: 21.359326502877487
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible perturbations in the system inputs, which were generally known as misclassifying attacks. By targeting the real-time processing capability, a new class of latency attacks are reported recently. They exploit new attack surfaces in object detectors by creating a computational bottleneck in the post-processing module, that leads to cascading failure and puts the real-time downstream tasks at risks. In this work, we take an initial attempt to defend against this attack via background-attentive adversarial training that is also cognizant of the underlying hardware capabilities. We first draw system-level connections between latency attack and hardware capacity across heterogeneous GPU devices. Based on the particular adversarial behaviors, we utilize objectness loss as a proxy and build background attention into the adversarial training pipeline, and achieve a reasonable balance between clean and robust accuracy. The extensive experiments demonstrate the defense effectiveness of restoring real-time processing capability from $13$ FPS to $43$ FPS on Jetson Orin NX, with a better trade-off between the clean and robust accuracy.

Related papers

• Real-Time Zero-Day Intrusion Detection System for Automotive Controller Area Network on FPGAs [13.581341206178525]
  This paper presents an unsupervised-learning-based convolutional autoencoder architecture for detecting zero-day attacks. We quantise the model using Vitis-AI tools from AMD/Xilinx targeting a resource-constrained Zynq Ultrascale platform. The proposed model successfully achieves equal or higher classification accuracy (> 99.5%) on unseen DoS, fuzzing, and spoofing attacks.
  arXiv  Detail & Related papers  (2024-01-19T14:36:01Z)
• Overload: Latency Attacks on Object Detection for Edge Devices [47.9744734181236]
  This paper investigates latency attacks on deep learning applications. Unlike common adversarial attacks for misclassification, the goal of latency attacks is to increase the inference time. We use object detection to demonstrate how such kind of attacks work.
  arXiv  Detail & Related papers  (2023-04-11T17:24:31Z)
• Intrusion Detection in Internet of Things using Convolutional Neural Networks [4.718295605140562]
  We propose a novel solution to the intrusion attacks against IoT devices using CNNs. The data is encoded as the convolutional operations to capture the patterns from the sensors data along time. The experimental results show significant improvement in both true positive rate and false positive rate compared to the baseline using LSTM.
  arXiv  Detail & Related papers  (2022-11-18T07:27:07Z)
• The Feasibility and Inevitability of Stealth Attacks [63.14766152741211]
  We study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence systems. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself.
  arXiv  Detail & Related papers  (2021-06-26T10:50:07Z)
• DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows [52.31831255787147]
  We introduce a novel technique, DAAIN, to detect out-of-distribution (OOD) inputs and adversarial attacks (AA) Our approach monitors the inner workings of a neural network and learns a density estimator of the activation distribution. Our model can be trained on a single GPU making it compute efficient and deployable without requiring specialized accelerators.
  arXiv  Detail & Related papers  (2021-05-30T22:07:13Z)
• IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking [70.14487738649373]
  Adrial attack arises due to the vulnerability of deep neural networks to perceive input samples injected with imperceptible perturbations. We propose a decision-based black-box attack method for visual object tracking. We validate the proposed IoU attack on state-of-the-art deep trackers.
  arXiv  Detail & Related papers  (2021-03-27T16:20:32Z)
• Hardware Accelerator for Adversarial Attacks on Deep Learning Neural Networks [7.20382137043754]
  A class of adversarial attack network algorithms has been proposed to generate robust physical perturbations. In this paper, we propose the first hardware accelerator for adversarial attacks based on memristor crossbar arrays.
  arXiv  Detail & Related papers  (2020-08-03T21:55:41Z)
• 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)
• Firearm Detection and Segmentation Using an Ensemble of Semantic Neural Networks [62.997667081978825]
  We present a weapon detection system based on an ensemble of semantic Convolutional Neural Networks. A set of simpler neural networks dedicated to specific tasks requires less computational resources and can be trained in parallel. The overall output of the system given by the aggregation of the outputs of individual networks can be tuned by a user to trade-off false positives and false negatives.
  arXiv  Detail & Related papers  (2020-02-11T13:58:16Z)
• Pelican: A Deep Residual Network for Network Intrusion Detection [7.562843347215287]
  We propose a deep neural network, Pelican, that is built upon specially-designed residual blocks. Pelican can achieve a high attack detection performance while keeping a much low false alarm rate.
  arXiv  Detail & Related papers  (2020-01-19T05:07:48Z)

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.