arXiv subjects

Johan Wahlstrom

Publications and source records attributed to Johan Wahlstrom.

5 recordsLinked to original sources

arXiv2024

A Human-in-the-Middle Attack against Object Detection Systems

Object detection systems using deep learning models have become increasingly popular in robotics thanks to the rising power of CPUs and GPUs in embedded systems. However, these models are susceptible to adversarial attacks. While some attacks are limited by strict assumptions on access to the detection system, we propose a novel hardware attack inspired by Man-in-the-Middle attacks in cryptography. This attack generates a Universal Adversarial Perturbations (UAP) and injects the perturbation between the USB camera and the detection system via a hardware attack. Besides, prior research is misled by an evaluation metric that measures the model accuracy rather than the attack performance. In combination with our proposed evaluation metrics, we significantly increased the strength of adversarial perturbations. These findings raise serious concerns for applications of deep learning models in safety-critical systems, such as autonomous driving.

cs.RO↗

arXiv2023

Adversarial Driving: Attacking End-to-End Autonomous Driving

As research in deep neural networks advances, deep convolutional networks become promising for autonomous driving tasks. In particular, there is an emerging trend of employing end-to-end neural network models for autonomous driving. However, previous research has shown that deep neural network classifiers are vulnerable to adversarial attacks. While for regression tasks, the effect of adversarial attacks is not as well understood. In this research, we devise two white-box targeted attacks against end-to-end autonomous driving models. Our attacks manipulate the behavior of the autonomous driving system by perturbing the input image. In an average of 800 attacks with the same attack strength (epsilon=1), the image-specific and image-agnostic attack deviates the steering angle from the original output by 0.478 and 0.111, respectively, which is much stronger than random noises that only perturbs the steering angle by 0.002 (The steering angle ranges from [-1, 1]). Both attacks can be initiated in real-time on CPUs without employing GPUs. Demo video: https://youtu.be/I0i8uN2oOP0.

cs.CV↗

arXiv2023

Adversarial Detection: Attacking Object Detection in Real Time

Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. Therefore, it is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. This paper bridges this gap by presenting the first real-time online attack against object detection models. We devise three attacks that fabricate bounding boxes for nonexistent objects at desired locations. The attacks achieve a success rate of about 90% within about 20 iterations. The demo video is available at https://youtu.be/zJZ1aNlXsMU.

cs.AI↗

arXiv2022

Distributed Black-box Attack: Do Not Overestimate Black-box Attacks

As cloud computing becomes pervasive, deep learning models are deployed on cloud servers and then provided as APIs to end users. However, black-box adversarial attacks can fool image classification models without access to model structure and weights. Recent studies have reported attack success rates of over 95% with fewer than 1,000 queries. Then the question arises: whether black-box attacks have become a real threat against cloud APIs? To shed some light on this, our research indicates that black-box attacks are not as effective against cloud APIs as proposed in research papers due to several common mistakes that overestimate the efficiency of black-box attacks. To avoid similar mistakes, we conduct black-box attacks directly on cloud APIs rather than local models.

cs.LG↗

arXiv2020

FootSLAM meets Adaptive Thresholding

Calibration of the zero-velocity detection threshold is an essential prerequisite for zero-velocity-aided inertial navigation. However, the literature is lacking a self-contained calibration method, suitable for large-scale use in unprepared environments without map information or pre-deployed infrastructure. In this paper, the calibration of the zero-velocity detection threshold is formulated as a maximum likelihood problem. The likelihood function is approximated using estimation quantities readily available from the FootSLAM algorithm. Thus, we obtain a method for adaptive thresholding that does not require map information, measurements from supplementary sensors, or user input. Experimental evaluations are conducted using data with different gait speeds, sensor placements, and walking trajectories. The proposed calibration method is shown to outperform fixed-threshold zero-velocity detectors and a benchmark using a speed-based threshold classifier.

eess.SP↗