Deep Neural Networks (DNNs) have shown impressive performance in computer vision tasks; however, their vulnerability to adversarial attacks raises concerns regarding their security and reliability. Extensive research has shown that DNNs can be compromised by carefully crafted perturbations, leading to significant performance degradation in both digital and physical domains. Therefore, ensuring the security of DNN-based systems is crucial, particularly in safety-critical domains such as autonomous driving, robotics, smart homes/cities, smart industries, video surveillance, and healthcare. In this paper, we present a comprehensive survey of the current trends focusing specifically on physical adversarial attacks. We aim to provide a thorough understanding of the concept of physical adversarial attacks, analyzing their key characteristics and distinguishing features. Furthermore, we explore the specific requirements and challenges associated with executing attacks in the physical world. Our article delves into various physical adversarial attack methods, categorized according to their target tasks in different applications, including classification, detection, face recognition, semantic segmentation and depth estimation. We assess the performance of these attack methods in terms of their effectiveness, stealthiness, and robustness. We examine how each technique strives to ensure the successful manipulation of DNNs while mitigating the risk of detection and withstanding real-world distortions. Lastly, we discuss the current challenges and outline potential future research directions in the field of physical adversarial attacks. We highlight the need for enhanced defense mechanisms, the exploration of novel attack strategies, the evaluation of attacks in different application domains, and the establishment of standardized benchmarks and evaluation criteria for physical adversarial attacks. Through this comprehensive survey, we aim to provide a valuable resource for researchers, practitioners, and policymakers to gain a holistic understanding of physical adversarial attacks in computer vision and facilitate the development of robust and secure DNN-based systems.

pdf/physical-adversarial-attacks-for-camera-based-smart-systems-fzo0y25ykw.pdf

Physical Adversarial Attacks for Camera-Based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook

There is a considerable threat present in genres such as machine learning due to adversarial attacks which include purposely feeding the system with data that will alter the decision region. These attacks are committed to presenting different data to machine learning models in a way that the model would be wrong in its classification or prediction. The field of study is still relatively young and has to develop strong bodies of scientific research that would eliminate the gaps in the current knowledge. This paper provides the literature review of adversarial attacks and defenses based on the highly cited articles and conference published in the Scopus database. Through the classification and assessment of 128 systematic articles: 80 original papers and 48 review papers till May 15, 2024, this study categorizes and reviews the literature from different domains, such as Graph Neural Networks, Deep Learning Models for IoT Systems, and others. The review posits findings on identified metrics, citation analysis, and contributions from these studies while suggesting the area’s further research and development for adversarial robustness’ and protection mechanisms. The identified objective of this work is to present the basic background of adversarial attacks and defenses, and the need for maintaining the adaptability of machine learning platforms. In this context, the objective is to contribute to building efficient and sustainable protection mechanisms for AI applications in various industries 

Adversarial Attacks in Machine Learning: Key Insights and Defense Approaches

The optical adversarial attack of deep neural network based on shadows

The reliability and robustness of lane detection play an instrumental role in the practical deployment of autonomous driving systems. Despite previous research indicating that adversarial examples can negatively affect lane detection models, leading to erroneous lane detection, most existing adversarial attacks are designed to attack lane detection models of a single deep learning-based task. To address this issue, we propose a toward cross-task physical adversarial attack via LED illumination modulation for lane detection systems (AdvLIM-LDs) by analyzing the common critical feature response mechanisms of lane detection models of different task types. The method first introduces a critical feature disruption (CFD) module to evaluate the impact of adversarial examples on critical features contributing to various tasks. Then, it utilizes the pulse width modulation of LEDs and the rolling shutter effect of CMOS image sensor to implant imperceptible adversarial perturbations during the image acquisition process. Finally, it enhances the cross-task transferability of adversarial examples by jointly optimizing a dual objective function composed of critical feature loss and model output accuracy loss. In digital domain simulations, adversarial examples generated by AdvLIM-LD caused an average detection accuracy degradation of 74.64% across lane detection models representing different task types, including the segmentation model SCNN, the anchor-based detector LaneATT, the curve-fitting model LSTR, and the keypoint detection model GANet. For cross-task attacks, the average accuracy degradation reached 55.37%. Physical-world experiments further validated the effectiveness of AdvLIM-LD, demonstrating its ability to degrade the source models’ average detection accuracy by over 80%.

AdvLIM-LD: Towards Cross-Task Physical Adversarial Attack via LED Illumination Modulation for Lane Detection Systems

Deep Neural Networks (DNNs) are highly vulnerable to disruptions caused by minimal noise, yet research on physical attacks leveraging light-based methods remains scarce. Light-based physical attacks are exceptionally stealthy, posing substantial security threats to vision-dependent applications such as autonomous driving. This paper enhances a state-of-the-art light-based physical attack that employs a genetic algorithm to optimize laser spot placement for maximum effectiveness. We expand the algorithm by introducing additional hyperparameters and systematically optimizing them to establish the most efficient workflow for this problem. To our knowledge, this is the first light-based attack capable of reliably performing physical attacks during daylight conditions, making it the most effective and robust approach of its kind. Extensive experiments conducted in a digital environment demonstrate the superiority of the genetic algorithm over random-location methods. By identifying optimal hyperparameter values, we achieve significant improvements in both performance and efficiency. Specifically, we managed to achieve an Attack Success Rate (ASR) of 89.7%, with an Average Query (AQ) of only 109.4, demonstrating a highly efficient and effective approach. The results reveal that laser spots can severely interfere with advanced DNNs, highlighting the critical security risks associated with this technique. 

Comprehensive analysis on laser spots adversarial attacks using genetic algorithm

Traffic sign recognition (TSR) system is essential for autonomous vehicle and is vulnerable to security threats from adversarial attacks. The existing adversarial attacks for TSR are invasive and suffer from poor concealment and high computational complexity, and thus have low feasibility in real-world scenarios. This paper proposes a non-invasive modulated LED illumination-based adversarial attack scheme. By generating luminance flashes imperceptible to human eyes through fast intensity modulation of lighting such as LED streetlights and exploiting the rolling shutter mechanism of CMOS sensors of in-vehicle imaging system, the proposed attack scheme can successfully perform adversarial attacks on TSR system by implanting luminance information perturbations into the images acquired by autonomous vehicle and thus poisoning the image data fed into TSR system. Depending on the modulation frequency and pattern of LED illumination, the proposed attack scheme enables denial of service (DoS) attack that leads to traffic sign detection failure and escape attack that leads to traffic sign misclassification, with the advantages of superior concealment, low computational complexity and high practical feasibility. Experiments are conducted with two benchmark datasets (GTSDB and GTSRB) and two state-of-the-art models of TSR detection and TSR classification, YOLOv5m and Sill-Net respectively, in both the digital and physical world. Experimental results show that the proposed DoS attack on the TSR detection model (YOLOv5m) can reach the success rate of 90.00% and the proposed escape attack on the TSR classification model (Sill-Net) can achieve the success rate of 35.00%.

MLIA: modulated LED illumination-based adversarial attack on traffic sign recognition system for autonomous vehicle

LIMA: Towards building a non-invasive and stealthy real-world adversarial attack model for traffic sign recognition systems.

A real world attack model combining LED modulation and attention-superpixel guidance

Lane detection is one of the fundamental technologies for autonomous driving, but it faces many security threats from adversarial attacks. Existing adversarial attacks against lane detection often simplify it as a certain type of computer vision task and ignore its cross-task characteristic, resulting in weak transferability, poor stealthiness, and low executability. This paper proposes a cross-task physical adversarial attack scheme based on LED illumination modulation (AdvLIM) after analyzing the decision behavior coexisting in lane detection models. We generate imperceptible brightness flicker through fast intensity modulation of LED illumination and utilize the rolling shutter effect of the CMOS image sensor to inject brightness information perturbations into the captured scene image. According to different modulation parameters, this paper proposes two attack strategies: scatter attack and dense attack. Cross-task attack experiments are conducted on the Tusimple dataset on five lane detection models of three different task types, including segmentation-based models (SCNN, RESA), point detection-based model (LaneATT), and curve-based models (LSTR, BézierLaneNet). The experimental results show that AdvLIM causes a detection accuracy drop of 77.93%, 75.86%, 51.51%, 89.41%, and 73.94% for the above models respectively. Experiments are also conducted in the physical world, and the results indicate that AdvLIM can pose a real and significant security threat to diverse lane detection systems in real-world scenarios. 

Cross-Task Physical Adversarial Attack Against Lane Detection System Based on LED Illumination Modulation

Although face recognition starts to play an important role in our daily life, we need to pay attention that data-driven face recognition vision systems are vulnerable to adversarial attacks. However, the current two categories of adversarial attacks, namely digital attacks and physical attacks both have drawbacks, with the former ones impractical and the latter one conspicuous, high-computational and inexecutable. To address the issues, we propose a practical, executable, inconspicuous and low computational adversarial attack based on LED illumination modulation. To fool the systems, the proposed attack generates imperceptible luminance changes to human eyes through fast intensity modulation of scene LED illumination and uses the rolling shutter effect of CMOS image sensors in face recognition systems to implant luminance information perturbation to the captured face images. In summary,we present a denial-of-service (DoS) attack for face detection and a dodging attack for face verification. We also evaluate their effectiveness against well-known face detection models, Dlib, MTCNN and RetinaFace , and face verification models, Dlib, FaceNet,and ArcFace.The extensive experiments show that the success rates of DoS attacks against face detection models reach 97.67%, 100%, and 100%, respectively, and the success rates of dodging attacks against all face verification models reach 100%. 

pdf/imperceptible-physical-attack-against-face-recognition-30xfzroid5.pdf

Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulation

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

You Jiang

Author Tools

Chat about Author