paper-with-me

홈 › Papers

fakeWeather: Adversarial Attacks for Deep Neural Networks Emulating Weather Conditions on the Camera Lens of Autonomous Systems

2022-05-27 · Alberto Marchisio, Giovanni Caramia, Maurizio Martina, Muhammad Shafique

Recently, Deep Neural Networks (DNNs) have achieved remarkable performances in many applications, while several studies have enhanced their vulnerabilities to malicious attacks. In this paper, we emulate the effects of natural weather conditions to introduce plausible perturbations that mislead the DNNs. By observing the effects of such atmospheric perturbations on the camera lenses, we model the patterns to create different masks that fake the effects of rain, snow, and hail. Even though the perturbations introduced by our attacks are visible, their presence remains unnoticed due to their association with natural events, which can be especially catastrophic for fully-autonomous and unmanned vehicles. We test our proposed fakeWeather attacks on multiple Convolutional Neural Network and Capsule Network models, and report noticeable accuracy drops in the presence of such adversarial perturbations. Our work introduces a new security threat for DNNs, which is especially severe for safety-critical applications and autonomous systems.

📄 PDF Abstract BibTeX arXiv:2205.13807

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Capsule Network A capsule is an activation vector that basically executes on its inputs some complex internal computations. Length of these activation vectors signifies the probability of…

Similar Papers 제목 키워드 기반

AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systems

2023-03-02 · Amira Guesmi, Muhammad Abdullah Hanif, Muhammad Shafique

Vision-based perception modules are increasingly deployed in many applications, especially autonomous vehicles and intelligent robots. These modules are being used to acquire information about the surroundings and identi…

Adversarial AttackAutonomous Vehicles

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

2024-03-26 · CVPR 2024 1 · Junhao Zheng, Chenhao Lin, Jiahao Sun, Zhengyu Zhao 외

Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks. Previous physical attacks against MDE models rely on 2D adversarial patch…

Adversarial AttackAutonomous DrivingDepth EstimationMonocular Depth Estimation

Distracting Downpour: Adversarial Weather Attacks for Motion Estimation

2023-05-11 · ICCV 2023 1 · Jenny Schmalfuss, Lukas Mehl, Andrés Bruhn

Current adversarial attacks on motion estimation, or optical flow, optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, adverse weather conditions constitute a much more re…

Motion EstimationOptical Flow Estimation

Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Models

2025-12-09 · Huzaifa Arif, Pin-Yu Chen, Alex Gittens, James Diffenderfer 외 arxiv

With the increasing reliance on AI models for weather forecasting, it is imperative to evaluate their vulnerability to adversarial perturbations. This work introduces Weather Adaptive Adversarial Perturbation Optimizatio…

Weather Forecasting

Quaternion-Hadamard Network: A Novel Defense Against Adversarial Attacks with a New Dataset

2025-02-12 · Vladimir Frants, Sos Agaian

This paper addresses the vulnerability of deep-learning models designed for rain, snow, and haze removal. Despite enhancing image quality in adverse weather, these models are susceptible to adversarial attacks that compr…

Denoisingimage-classificationImage ClassificationSSIM+1