This page features comprehensive surveys and review articles that map the evolving landscape of secure and resilient AI. These resources offer valuable overviews of existing methodologies, systematized taxonomies, and identified research gaps to guide further investigation and development.
| Title | Publisher | Year | Description | Link |
|---|---|---|---|---|
| An Introduction to Adversarially Robust Deep Learning | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2024 | This work presents a comprehensive survey of adversarial machine learning since 2013, covering key attack and defense strategies, taxonomies, and theoretical insights into adversarial robustness, fragility, and certification. | IEEE Xplore |
| The Impact of Adversarial Attacks on Federated Learning: A Survey | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2024 | This paper presents a hybrid deep learning framework that combines convolutional neural networks (CNNs) and transformers to enhance the accuracy and robustness of medical image segmentation, particularly in challenging scenarios with limited data. | IEEE Xplore |
| Physical Adversarial Attack Meets Computer Vision: A Decade Survey | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2024 | This work introduces the concept of the “adversarial medium” as a physical carrier of perturbations, proposes a hexagonal indicator (hiPAA) to evaluate physical adversarial attacks across six key dimensions, and presents comparative results for vehicle and person detection tasks. | IEEE Xplore |
| Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2023 | This paper categorizes dataset vulnerabilities and security threats, addressing attacks during training and testing phases, and explores defense mechanisms against dataset tampering. | IEEE Xplore |
| Physical Adversarial Attacks for Surveillance: A Survey | IEEE Transactions On Neural Networks And Learning System | 2024 | This work reviews recent advances in physical adversarial attacks for surveillance tasks, categorizes them into human-designed and deep learning–based methods, and analyzes their impact across multi-modal sensing modalities including RGB, infrared, LiDAR, and multispectral data. | IEEE Xplore |
| Unraveling Attacks to Machine-Learning-Based IoT Systems: A Survey and the Open Libraries Behind Them | IEEE Internet of Things Journal | 2024 | This work explores six key attack types targeting ML-based IoT systems, categorizes threat models and attack vectors, and provides supporting resources including open-source libraries for analysis and defense. | IEEE Xplore |
| How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses | IEEE Access | 2024 | This work compiles recent adversarial attacks in object recognition based on attacker knowledge, reviews modern defenses by strategy, and discusses impacts on Vision Transformers, practical applications like autonomous driving, and related datasets and metrics. | IEEE Xplore |
| A Survey on Attacks and Their Countermeasures in Deep Learning: Applications in Deep Neural Networks, Federated, Transfer, and Deep Reinforcement Learning | IEEE Access | 2023 | This survey comprehensively analyzes attacks and defenses across Deep Neural Networks, Federated Learning, Transfer Learning, and Deep Reinforcement Learning, covering diverse threat models, mitigation strategies, and evaluating across application domains, datasets, and testbeds. | IEEE Xplore |
| Physical Adversarial Attacks for Camera-Based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook | IEEE Access | 2023 | This work surveys physical adversarial attack methods for camera-based smart systems, categorizing them by target task, such as classification, detection, face recognition, semantic segmentation, and depth estimation, and evaluates their performance based on effectiveness, stealthiness, and robustness. | IEEE Xplore |
| Defense strategies for Adversarial Machine Learning: A survey | Computer Science Review | 2023 | This paper surveys recent adversarial attacks in object recognition, categorizing them by attacker knowledge, and reviews modern defenses by protection strategy, with discussions on Vision Transformers, evaluation datasets, metrics, and applications like autonomous driving. | Elsevier |
| A systematic survey of attack detection and prevention in connected and autonomous vehicles | Vehicular Communications Elsevier | 2022 | This paper provides a comprehensive overview of attack detection and prevention strategies in connected and autonomous vehicles (CAVs). It categorizes various attack types, such as in-vehicle network and inter-vehicle communication attacks, and evaluates existing detection and prevention mechanisms. The authors highlight the need for robust security frameworks to address evolving cyber threats in CAV systems. | Elsevier |
| Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective | arXiV | 2024 | This paper provides a systematic survey of adversarial attacks across the machine learning lifecycle (training, deployment, and inference) offering a unified framework to understand and compare attack methods. | arXiv |
| On the adversarial robustness of multi-modal foundation models | arXiv | 2023 | This paper demonstrates that imperceptible perturbations to input images can manipulate the outputs of multi-modal foundation models, such as Flamingo, leading to misleading captions that may direct users to malicious websites or disseminate false information. These findings highlight the necessity for implementing countermeasures against adversarial attacks in deployed multi-modal models. | arXiv |
| Adversarial Machine Learning: A Survey | arXiV | 2023 | This paper offers a comprehensive survey of adversarial defenses across the machine learning lifecycle (pre-training, training, post-training, deployment, and inference) categorizing methods against backdoor attacks, weight attacks, and adversarial examples within a unified framework. | arXiv |
| A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap? | arXiV | 2022 | This work systematically reviews non-adversarial robustness in deep learning for computer vision, addressing definitions, evaluation datasets, robustness metrics, and key defense strategies. | arXiv |
| Communication-Efficient Edge AI: Algorithms and Systems | IEEE Communications Surveys & Tutorials | 2020 | To address the bottlenecks of decentralized data processing, this paper explores the latest communication-efficient strategies for deploying intelligent AI applications across edge devices and servers. | IEEE Xplore |
| Edge Intelligence: Empowering Intelligence to the Edge of Network | Proceedings of the IEEE | 2021 | This survey provides a roadmap for the rapidly expanding field of edge intelligence, showing how we can bring faster, more secure AI processing directly to the devices where data is actually created. | IEEE Xplore |
| Edge Computing with Artificial Intelligence: A Machine Learning Perspective | ACM Computing Surveys | 2023 | By integrating artificial intelligence with edge computing, this research overcomes the limitations of traditional networks to create a faster, smarter infrastructure capable of handling the massive data demands of our increasingly connected world. | ACM Digital Library |
| A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services | IEEE Communications Surveys & Tutorials | 2023 | To overcome the massive energy drain caused by processing terabytes of sensor data, this study explores how “Approximate Edge AI” can make high-performance autonomous driving more sustainable and efficient for low-power vehicles. | IEEE Xplore |
| Review of Lightweight Deep Convolutional Neural Networks | Archives of Computational Methods in Engineering | 2024 | This review explores how lightweight neural networks shrink powerful AI to fit on mobile hardware, bridging the gap between high-performance computing and the practical needs of everyday portable technology. | Springer Nature Link |
| Near-Edge Computing Aware Object Detection: A Review | IEEE Access | 2023 | By optimizing large AI models for smaller hardware, this review paves the way for drones and autonomous vehicles to perceive and react to the world in real-time without being limited by the low processing power. | IEEE Xplore |
| Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review | Proceedings of the IEEE | 2023 | This paper surveys the cutting-edge methods that enable powerful deep learning models to run efficiently on those same resource-constrained devices, unlocking real-time AI applications without the latency, cost, and privacy risks of cloud computing. | IEEE Xplore |
| Edge AI: A survey | Internet of Things and Cyber-Physical Systems | 2023 | This papers explores how Edge AI enables real-time, secure automation for applications covering rom self-driving cars to smart healthcare, on hardware with limited computing power. | Elsevier |
| Exploring Shared Perception and Control in Cooperative Vehicle-Intersection Systems: A Review | IEEE Transactions on Intelligent Transportation Systems | 2024 | This research outlines how smart roads and cars can communicate to each other to perfectly coordinate their movements, to enable autonomous vehicles navigate crowded intersections making future commutes safer, faster, and more sustainable. | IEEE Xplore |
| Vision transformer models for mobile/edge devices: a survey | Multimedia Systems | 2024 | This paper bridges the gap between powerful AI and everyday devices by showing how to reduce massive Vision Transformer models into compact, fast versions that bring high-performance computer vision to mobile and edge devices. | Springer Nature Link |
| Green Edge AI: A Contemporary Survey | Proceedings of the IEEE | 2024 | This paper provides a roadmap for green edge AI, ensuring that powerful artificial intelligence can run locally on wireless networks with minimal effects on on battery life and processing speed. | IEEE Xplore |
| A comprehensive survey of deep learning-based lightweight object detection models for edge devices | Artificial Intelligence Review | 2024 | This paper provides a roadmap for building faster, smaller AI models that allow edge devices to recognize objects instantly without relying on powerful, energy-intensive servers. | Springer Nature Link |
| Computation-efficient deep learning for computer vision: A survey | Cybernetics and Intelligence | 2024 | To make powerful AI practical for everyday technology, this survey explores how to shrink massive deep learning models so they can run faster and use less energy without sacrificing their human-level intelligence. | IEEE Xplore |
| Decentralized and Distributed Learning for AIoT: A Comprehensive Review, Emerging Challenges, and Opportunities | IEEE Access | 2024 | By shifting from central data storage to collaborative, decentralized learning, this paper shows how smart devices can now train powerful AI together without ever compromising user privacy or overloading the network. | IEEE Xplore |
| Edge Intelligence for Internet of Vehicles: A Survey | IEEE Transactions on Consumer Electronics | 2024 | This survey explores how Edge Intelligence solves the data traffic jam of modern vehicles by moving AI processing out of distant clouds and directly onto the street level for instant, real-time decision-making. | IEEE Xplore |
| Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions | ACM Computing Surveys | 2025 | This paper explores how TinyML optimization techniques can reduce the size of powerful object detection into ultra-low-power microcontrollers, enabling billions of everyday IoT devices to perceive and process the world locally without requiring extensive amounts of energy. | ACM Digital Library |
| Comprehensive review of deep learning-based tiny object detection: challenges, strategies, and future directions | Knowledge and Information Systems | 2025 | This paper explores how modern AI is moving beyond the limitations of traditional vision systems to accurately identify tiny objects, from detecting early-stage tumors in medical scans to identifying hazards in autonomous driving. | Springer Nature Link |
| Lightweight deep learning for visual perception: A survey of models, compression strategies, and edge deployment challenges | Neurocomputing | 2025 | This survey bridges the gap between powerful AI and everyday smart devices by developing lightweight deep learning models that allow resource-heavy tasks such as object detection and image recognition to run smoothly on compact edge devices without sacrificing speed or accuracy. | Elsevier |
| Vision transformers on the edge: A comprehensive survey of model compression and acceleration strategies | Neurocomputing | 2025 | This survey bridges the gap between powerful AI and portable technology by providing a roadmap for reducing the size of complex vision transformers to run efficiently on everyday edge devices without sacrificing accuracy. | Elsevier |
| Vision-Language Models for Edge Networks: A Comprehensive Survey | IEEE Internet of Things Journal | 2025 | This paper explores how to reduce powerful vision-language AI to run directly on everyday devices, bringing advanced intelligence to the real world without relying on massive computing power. | IEEE Xplore |
| AI Safety Assurance for Automated Vehicles: A Survey on Research, Standardization, Regulation | IEEE Transactions on Intelligent Vehicles | 2025 | This paper bridges the gap between cutting-edge AI innovation and public safety by providing a unified roadmap that aligns research, industry standards, and government regulations for the next generation of self-driving cars. | IEEE Xplore |
| Emerging trends and strategic opportunities in tiny machine learning: A comprehensive thematic analysis | Neurocomputing | 2025 | By mapping the vast landscape of Tiny Machine Learning through hundreds of research papers, this study uncovers the essential breakthroughs needed to bring powerful AI to everyday, low-power devices without relying on the cloud. | Elsevier |
| A Survey on Trustworthy Edge Intelligence: From Security and Reliability to Transparency and Sustainability | IEEE Communications Surveys & Tutorials | 2025 | This survey provides a comprehensive blueprint for ensuring decentralized systems remain reliable, transparent, and resilient against the unique challenges of the modern digital world. | IEEE Xplore |
| Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models | ACM Computing Surveys | 2025 | This paper provides a roadmap for bringing powerful artificial intelligence directly onto everyday devices, enabling faster, more private, and more efficient technology that works in real time without relying on the cloud. | ACM Digital Library |
| A Review of Trustworthy and Explainable Artificial Intelligence (XAI) | IEEE Access | 2023 | This review provides a vital blueprint for building transparent, unbiased, and explainable systems to ensure human safety and data security across critical industries such as healthcare and autonomous driving. | IEEE Xplore |
| Trustworthy AI: From Principles to Practices | ACM Computing Surveys | 2023 | To bridge the gap between AI’s potential and its risks, this paper provides a complete roadmap for building reliable systems that prioritize fairness, privacy, and security at every step of their development. | ACM Digital Library |
| Toward Trustworthy Artificial Intelligence (TAI) in the Context of Explainability and Robustness | ACM Computing Surveys | 2025 | This survey explores how the gap between complex “black-box” algorithms and human safety can be bridged, by providing a roadmap for building AI systems that are fundamentally transparent, robust, and ethically aligned with society. | ACM Digital Library |
| Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models | ACM Computing Surveys | 2026 | This review provides a new framework for identifying and addressing hidden risks such as bias and opacity, to ensure that powerful AI models are both safe and reliable. A practical roadmap is created for building technology that society can actually trust. | ACM Digital Library |
| Trust and transparency in AI: industry voices on data, ethics, and compliance | AI & Society | 2025 | As the EU moves toward stricter regulation, this paper bridges the gap between high-level ethics and real-world applications by identifying the practical hurdles companies face when trying to build AI that is not only legally compliant but also socially responsible and safe. | Springer Nature Link |