- Only included surveys after 2020;
- Surveys with low H-Index and fewer than 20 pages are excluded;
- Double column
- H-Index: 240
- Country: US
A Survey of Adversarial Attack and Defense Methods for Malware Classification in Cyber Security (2023, 30 pages)
- INTRODUCTION
- UNIFIED MALWARE CLASSIFICATION FRAMEWORK
- ML-BASED MALWARE CLASSIFICATION
- ADVERSARIAL ATTACKS ON ML-BASED MALWARE CLASSIFIERS
- ENHANCING ADVERSARIAL ROBUSTNESS OF ML-BASED MALWARE CLASSIFIERS
- FUTURE WORK DIRECTIONS
- CONCLUSION
Adversarial Machine Learning for Network Intrusion Detection Systems: A Comprehensive Survey (2023, 29)
- INTRODUCTION
- EXISTING SURVEYS AND OUR CONTRIBUTIONS
- TAXONOMY OF NIDS
- ADVERSARIAL ATTACKS
- ADVERSARIAL DEFENCES AND ITS APPLICABILITY IN NIDS
- LESSONS LEARNED AND FUTURE RESEARCH DIRECTIONS
- CONCLUSION
Adversarial Machine Learning: A Multilayer Review of the State-of-the-Art and Challenges for Wireless and Mobile Systems (2022, 37)
- INTRODUCTION
- CHALLENGES IN ADVERSARIAL DESIGN IN MOBILE AND WIRELESS NETWORKS
- REVISITING ADVERSARIAL ML METHODS:AN OUTLOOK ON WIRELESS AND MOBILE SYSTEMS
- ADVERSARIAL MACHINE LEARNING APPLICATIONS TO MOBILE NETWORKS AND SYSTEMS
- LESSONS LEARNED,OPEN ISSUES AND CHALLENGES
- SUMMARY AND CONCLUSION
- INTRODUCTION
- RELATED SURVEYS
- MACHINE LEARNING ALGORITHMS AND THEIR PERFORMANCE
- ADVANTAGES AND EXPLOITATIONS OF ML-BASED ATTACKS
- SMART ATTACKS BASED ON DATA ANALYSIS
- SMART ATTACKS BASED ON BEHAVIORAL DETECTION
- SMART ATTACKS BASED ON DATA GENERATION
- SMART ATTACKS BASED ON BEHAVIORAL DIVERSION
- DISCUSSIONS
- CONCLUSION
Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS (2021, 29)
- INTRODUCTION
- OVERVIEW OF MACHINE LEARNING
- ML APPLICATIONS IN CPS
- ML FOR RESILIENT CPS
- ADVERSARIAL MACHINE LEARNING (AML) AND CPS
- SECURE/RESILIENT ML
- OPEN RESEARCH CHALLENGES AND FUTURE DIRECTIONS
- CONCLUSION
Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and the Way Forward (2020, 29)
- INTRODUCTION
- CONNECTED AND AUTONOMOUS VEHICLES (CAVS): HISTORY,INTRODUCTION, AND CHALLENGES
- THE ML PIPELINE IN CAVS
- ADVERSARIAL ML ATTACKS AND THE ADVERSARIAL ML THREAT FOR CAVS
- TOWARDS DEVELOPING ADVERSARIALLY ROBUST ML SOLUTIONS
- OPEN RESEARCH ISSUES
- CONCLUSION
- Double column
- H-Index: 234
- Country: US
- INTRODUCTION
- BACKGROUND & DEFINITION
- CATEGORIZATION AND FRAMEWORKS
- RECURRENT GRAPH NEURAL NETWORKS
- CONVOLUTIONAL GRAPH NEURAL NETWORKS
- GRAPH AUTOENCODERS
- SPATIAL-TEMPORAL GRAPH NEURAL NETWORKS
- APPLICATIONS
- FUTURE DIRECTIONS
- CONCLUSION
- Double column
- H-Index: 233
- Country: UK
A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies (2022, 11)
- Introduction
- Fundamentals
- General adversarial training with gradient regularization
- Methodologies
- Further research issues
- Conclusion
- Double column
- H-Index: 204
- Country: US
Adversarial Deep Learning: A Survey on Adversarial Attacks and Defense Mechanisms on Image Classification (2022, 26)
- INTRODUCTION
- DEFINITIONS OF TERMS
- BACKGROUND
- ADVERSARIAL THREAT MODEL
- ATTACK STRATEGIES
- DEFENSE STRATEGIES
- DISCUSSION & FUTURE RESEARCH DIRECTION
- CONCLUSION
Adversarial Machine Learning Applied to Intrusion and Malware Scenarios: A Systematic Review (2020, 17)
- INTRODUCTION
- BACKGROUND KNOWLEDGE
- ADVERSARIAL ATTACK STRATEGIES
- ADVERSARIAL DEFENSES
- APPLICATIONS TO INTRUSION AND MALWARE SCENARIOS
- CONCLUSION
- Double column
- H-Index: 190
- Country: US
- INTRODUCTION
- GRAPH
- ADVERSARIAL ATTACKS ON GRAPH DATA
- ADVERSARIAL DEFENSE ON GRAPH DATA
- METRICS
- DATASET AND APPLICATION
- CONCLUSION
- Single column
- H-Index: 190
- Country: 190
- INTRODUCTION
- BACKGROUND OF ADVERSARIAL EXAMPLES
- MODEL PERSPECTIVE
- DATA PERSPECTIVE
- OTHER PERSPECTIVES
- CURRENT PROBLEMS AND FUTURE DIRECTIONS
- CONCLUSION
- INTRODUCTION
- A GENERAL OVERVIEW OF ADVERSARIAL ATTACKS
- TAXONOMY OF ADVERSARIAL DEFENSES
- ADVERSARIAL TRAINING-BASED DEFENSES
- PERTURBATION CONTROL-BASED DEFENSES
- ROBUSTNESS BY CERTIFICATION
- MISCELLANEOUS
- METRICS FOR EVALUATION
- ADVERSARIAL DATASETS AND FRAMEWORKS
- RECOMMENDATIONS FOR FUTURE WORK
- CONCLUSION
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning (2023, 39)
- INTRODUCTION
- MODELING POISONING ATTACKS AND DEFENSES
- ATTACK
- DEFENSES
- POISONING ATTACKS AND DEFENSES IN OTHER DOMAINS
- RESOURCES: SOFTWARE LIBRARIES, IMPLEMENTATIONS, AND BENCHMARKS
- DEVELOPMENT, CHALLENGES, AND FUTURE RESEARCH DIRECTIONS
- CONCLUDING REMARKS
- INTRODUCTION
- PRELIMINARY
- ADVERSARIAL ATTACKS
- ADVERSARIAL DEFENSES
- EXPLANATIONS FOR THE PHENOMENON OF ADVERSARIAL EXAMPLES
- DATASETS
- FUTURE DIRECTIONS
- CONCLUSIONS
- INTRODUCTION
- BACKGROUNDS AND CATEGORIZATION
- USER-ITEM COLLABORATIVE FILTERING
- SEQUENTIAL RECOMMENDATION
- SOCIAL RECOMMENDATION
- KNOWLEDGE-GRAPH-BASED RECOMMENDATION
- OTHER TASKS
- DATASETS, EVALUATION METRICS, AND APPLICATIONS
- FUTURE RESEARCH DIRECTIONS AND OPEN ISSUES
- CONCLUSION
- INTRODUCTION
- PRELIMINARY DISCUSSION: THE DIFFERENCES BETWEEN ADVERSARIAL ATTACKS IN THE COMPUTER VISION AND CYBER SECURITY DOMAINS
- TAXONOMY
- ADVERSARIAL ATTACKS IN THE CYBER SECURITY DOMAIN
- ADVERSARIAL DEFENSE METHODS IN THE CYBER SECURITY DOMAIN
- CURRENT GAPS AND FUTURE RESEARCH DIRECTIONS FOR ADVERSARIAL LEARNING IN THE CYBER SECURITY DOMAIN
- CONCLUSION
Adversarial Machine Learning in Image Classification: A Survey Toward the Defender’s Perspective (2021, 38)
- INTRODUCTION
- BACKGROUND
- ADVERSARIAL IMAGES AND ATTACKS
- DEFENSES AGAINST ADVERSARIAL ATTACKS
- EXPLANATIONS FOR THE EXISTENCE OF ADVERSARIAL EXAMPLES
- PRINCIPLES FOR DESIGNING AND EVALUATING DEFENSES
- DIRECTIONS OF FUTURE WORK
- FINAL CONSIDERATIONS
- Double column
- H-Index: 182
- Country: Netherlands
- INTRODUCTION
- COMPONENTS OF AD SYSTEM
- REINFORCEMENT LEARNING
- EXTENSIONS TO REINFORCEMENT LEARNING
- REINFORCEMENT LEARNING FOR AUTONOMOUS DRIVING TASKS
- REAL WORLD CHALLENGES AND FUTURE PERSPECTIVES
- CONCLUSION
- Double column
- H-Index: 177
- Country: Netherlands
- Introduction
- Definitions and notations
- Adversarial attacks
- Adversarial defense
- Discussion
- Conclusions
- Introduction
- Textual adversarial example
- Textual adversarial attack
- Textual adversarial attack application
- Defense against textual adversarial attack
- Conclusion
- Double column
- H-Index: 112
- Country: UK
A survey on adversarial attacks in computer vision: Taxonomy, visualization and future directions (2022, 17)
- Introduction
- Related work
- Preliminaries
- Exploration of adversarial attacks based on taxonomy
- Construction of knowledge graph
- Field visualization
- Trends and directions
- Conclusion
- Single column
- H-Index: 101
- Country: Netherlands
- Introduction
- Related work
- Adversarial attacks and defense methods
- Adversarial example detection methods
- Experiment settings
- Results and discussions
- Challenges, future perspectives, and conclusion
- Single column
- H-Index: 62
- Country: Switzerland
- Introduction
- Background
- Adversarial Attack
- Adversarial Defense
- Discussion
- Conclusions
- Introduction
- Adversarial Attack
- Adversarial Example Defense
- Challenge
- Conclusions
- Double column
- H-Index: 60
- Country: Ireland
- Introduction
- Literature collection and related work
- Adversarial machine learning attacks
- Adversarial machine learning defenses
- Evaluation of defense methods
- Discussion
- Single column
- H-Index: 49
- Switzerland
Adversarial Machine Learning Attacks against Intrusion Detection Systems: A Survey on Strategies and Defense (2023, 34)
- Introduction
- Related Surveys
- Intrusion Detection System Based on ML
- Adversarial Machine Learning
- Machine Learning Adversaries against IDS
- Benchmark Datasets
- Defense Strategies
- Challenges and Future Directions
- Conclusions