Skip to content

Instantly share code, notes, and snippets.

@changx03
Last active September 10, 2023 10:26
Show Gist options
  • Save changx03/cdd07fd413ee94cfc06898dde51b3e1f to your computer and use it in GitHub Desktop.
Save changx03/cdd07fd413ee94cfc06898dde51b3e1f to your computer and use it in GitHub Desktop.

Structure of most recent surveys on adversarial attacks and defenses

  • Only included surveys after 2020;
  • Surveys with low H-Index and fewer than 20 pages are excluded;

IEEE Communications Surveys & Tutorials

  • Double column
  • H-Index: 240
  • Country: US

A Survey of Adversarial Attack and Defense Methods for Malware Classification in Cyber Security (2023, 30 pages)

  1. INTRODUCTION
  2. UNIFIED MALWARE CLASSIFICATION FRAMEWORK
  3. ML-BASED MALWARE CLASSIFICATION
  4. ADVERSARIAL ATTACKS ON ML-BASED MALWARE CLASSIFIERS
  5. ENHANCING ADVERSARIAL ROBUSTNESS OF ML-BASED MALWARE CLASSIFIERS
  6. FUTURE WORK DIRECTIONS
  7. CONCLUSION

Adversarial Machine Learning for Network Intrusion Detection Systems: A Comprehensive Survey (2023, 29)

  1. INTRODUCTION
  2. EXISTING SURVEYS AND OUR CONTRIBUTIONS
  3. TAXONOMY OF NIDS
  4. ADVERSARIAL ATTACKS
  5. ADVERSARIAL DEFENCES AND ITS APPLICABILITY IN NIDS
  6. LESSONS LEARNED AND FUTURE RESEARCH DIRECTIONS
  7. CONCLUSION

Adversarial Machine Learning: A Multilayer Review of the State-of-the-Art and Challenges for Wireless and Mobile Systems (2022, 37)

  1. INTRODUCTION
  2. CHALLENGES IN ADVERSARIAL DESIGN IN MOBILE AND WIRELESS NETWORKS
  3. REVISITING ADVERSARIAL ML METHODS:AN OUTLOOK ON WIRELESS AND MOBILE SYSTEMS
  4. ADVERSARIAL MACHINE LEARNING APPLICATIONS TO MOBILE NETWORKS AND SYSTEMS
  5. LESSONS LEARNED,OPEN ISSUES AND CHALLENGES
  6. SUMMARY AND CONCLUSION

How Machine Learning Changes the Nature of Cyberattacks on IoT Networks: A Survey (2022, 31)

  1. INTRODUCTION
  2. RELATED SURVEYS
  3. MACHINE LEARNING ALGORITHMS AND THEIR PERFORMANCE
  4. ADVANTAGES AND EXPLOITATIONS OF ML-BASED ATTACKS
  5. SMART ATTACKS BASED ON DATA ANALYSIS
  6. SMART ATTACKS BASED ON BEHAVIORAL DETECTION
  7. SMART ATTACKS BASED ON DATA GENERATION
  8. SMART ATTACKS BASED ON BEHAVIORAL DIVERSION
  9. DISCUSSIONS
  10. CONCLUSION

Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS (2021, 29)

  1. INTRODUCTION
  2. OVERVIEW OF MACHINE LEARNING
  3. ML APPLICATIONS IN CPS
  4. ML FOR RESILIENT CPS
  5. ADVERSARIAL MACHINE LEARNING (AML) AND CPS
  6. SECURE/RESILIENT ML
  7. OPEN RESEARCH CHALLENGES AND FUTURE DIRECTIONS
  8. CONCLUSION

Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and the Way Forward (2020, 29)

  1. INTRODUCTION
  2. CONNECTED AND AUTONOMOUS VEHICLES (CAVS): HISTORY,INTRODUCTION, AND CHALLENGES
  3. THE ML PIPELINE IN CAVS
  4. ADVERSARIAL ML ATTACKS AND THE ADVERSARIAL ML THREAT FOR CAVS
  5. TOWARDS DEVELOPING ADVERSARIALLY ROBUST ML SOLUTIONS
  6. OPEN RESEARCH ISSUES
  7. CONCLUSION

IEEE Transactions on Neural Networks and Learning Systems

  • Double column
  • H-Index: 234
  • Country: US

A Comprehensive Survey on Graph Neural Networks (2021, 23)

  1. INTRODUCTION
  2. BACKGROUND & DEFINITION
  3. CATEGORIZATION AND FRAMEWORKS
  4. RECURRENT GRAPH NEURAL NETWORKS
  5. CONVOLUTIONAL GRAPH NEURAL NETWORKS
  6. GRAPH AUTOENCODERS
  7. SPATIAL-TEMPORAL GRAPH NEURAL NETWORKS
  8. APPLICATIONS
  9. FUTURE DIRECTIONS
  10. CONCLUSION

Elsevier Pattern Recognition

  • Double column
  • H-Index: 233
  • Country: UK

A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies (2022, 11)

  1. Introduction
  2. Fundamentals
  3. General adversarial training with gradient regularization
  4. Methodologies
  5. Further research issues
  6. Conclusion

IEEE Access

  • Double column
  • H-Index: 204
  • Country: US

Adversarial Deep Learning: A Survey on Adversarial Attacks and Defense Mechanisms on Image Classification (2022, 26)

  1. INTRODUCTION
  2. DEFINITIONS OF TERMS
  3. BACKGROUND
  4. ADVERSARIAL THREAT MODEL
  5. ATTACK STRATEGIES
  6. DEFENSE STRATEGIES
  7. DISCUSSION & FUTURE RESEARCH DIRECTION
  8. CONCLUSION

Adversarial Machine Learning Applied to Intrusion and Malware Scenarios: A Systematic Review (2020, 17)

  1. INTRODUCTION
  2. BACKGROUND KNOWLEDGE
  3. ADVERSARIAL ATTACK STRATEGIES
  4. ADVERSARIAL DEFENSES
  5. APPLICATIONS TO INTRUSION AND MALWARE SCENARIOS
  6. CONCLUSION

IEEE Transactions on Knowledge and Data Engineering

  • Double column
  • H-Index: 190
  • Country: US

Adversarial Attack and Defense on Graph Data: A Survey (2023, 19)

  1. INTRODUCTION
  2. GRAPH
  3. ADVERSARIAL ATTACKS ON GRAPH DATA
  4. ADVERSARIAL DEFENSE ON GRAPH DATA
  5. METRICS
  6. DATASET AND APPLICATION
  7. CONCLUSION

ACM Computing Surveys

  • Single column
  • H-Index: 190
  • Country: 190

Interpreting Adversarial Examples in Deep Learning: A Review (2023, 38)

  1. INTRODUCTION
  2. BACKGROUND OF ADVERSARIAL EXAMPLES
  3. MODEL PERSPECTIVE
  4. DATA PERSPECTIVE
  5. OTHER PERSPECTIVES
  6. CURRENT PROBLEMS AND FUTURE DIRECTIONS
  7. CONCLUSION

A Survey of Adversarial Defenses and Robustness in NLP (2023, 39)

  1. INTRODUCTION
  2. A GENERAL OVERVIEW OF ADVERSARIAL ATTACKS
  3. TAXONOMY OF ADVERSARIAL DEFENSES
  4. ADVERSARIAL TRAINING-BASED DEFENSES
  5. PERTURBATION CONTROL-BASED DEFENSES
  6. ROBUSTNESS BY CERTIFICATION
  7. MISCELLANEOUS
  8. METRICS FOR EVALUATION
  9. ADVERSARIAL DATASETS AND FRAMEWORKS
  10. RECOMMENDATIONS FOR FUTURE WORK
  11. CONCLUSION

Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning (2023, 39)

  1. INTRODUCTION
  2. MODELING POISONING ATTACKS AND DEFENSES
  3. ATTACK
  4. DEFENSES
  5. POISONING ATTACKS AND DEFENSES IN OTHER DOMAINS
  6. RESOURCES: SOFTWARE LIBRARIES, IMPLEMENTATIONS, AND BENCHMARKS
  7. DEVELOPMENT, CHALLENGES, AND FUTURE RESEARCH DIRECTIONS
  8. CONCLUDING REMARKS

Adversarial Attacks and Defenses in Deep Learning: From a Perspective of Cybersecurity (2022, 39)

  1. INTRODUCTION
  2. PRELIMINARY
  3. ADVERSARIAL ATTACKS
  4. ADVERSARIAL DEFENSES
  5. EXPLANATIONS FOR THE PHENOMENON OF ADVERSARIAL EXAMPLES
  6. DATASETS
  7. FUTURE DIRECTIONS
  8. CONCLUSIONS

Graph Neural Networks in Recommender Systems: A Survey (2022, 37)

  1. INTRODUCTION
  2. BACKGROUNDS AND CATEGORIZATION
  3. USER-ITEM COLLABORATIVE FILTERING
  4. SEQUENTIAL RECOMMENDATION
  5. SOCIAL RECOMMENDATION
  6. KNOWLEDGE-GRAPH-BASED RECOMMENDATION
  7. OTHER TASKS
  8. DATASETS, EVALUATION METRICS, AND APPLICATIONS
  9. FUTURE RESEARCH DIRECTIONS AND OPEN ISSUES
  10. CONCLUSION

Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain (2021, 36)

  1. INTRODUCTION
  2. PRELIMINARY DISCUSSION: THE DIFFERENCES BETWEEN ADVERSARIAL ATTACKS IN THE COMPUTER VISION AND CYBER SECURITY DOMAINS
  3. TAXONOMY
  4. ADVERSARIAL ATTACKS IN THE CYBER SECURITY DOMAIN
  5. ADVERSARIAL DEFENSE METHODS IN THE CYBER SECURITY DOMAIN
  6. CURRENT GAPS AND FUTURE RESEARCH DIRECTIONS FOR ADVERSARIAL LEARNING IN THE CYBER SECURITY DOMAIN
  7. CONCLUSION

Adversarial Machine Learning in Image Classification: A Survey Toward the Defender’s Perspective (2021, 38)

  1. INTRODUCTION
  2. BACKGROUND
  3. ADVERSARIAL IMAGES AND ATTACKS
  4. DEFENSES AGAINST ADVERSARIAL ATTACKS
  5. EXPLANATIONS FOR THE EXISTENCE OF ADVERSARIAL EXAMPLES
  6. PRINCIPLES FOR DESIGNING AND EVALUATING DEFENSES
  7. DIRECTIONS OF FUTURE WORK
  8. FINAL CONSIDERATIONS

IEEE Transactions on Intelligent Transportation Systems

  • Double column
  • H-Index: 182
  • Country: Netherlands

Deep Reinforcement Learning for Autonomous Driving: A Survey (2022, 18)

  1. INTRODUCTION
  2. COMPONENTS OF AD SYSTEM
  3. REINFORCEMENT LEARNING
  4. EXTENSIONS TO REINFORCEMENT LEARNING
  5. REINFORCEMENT LEARNING FOR AUTONOMOUS DRIVING TASKS
  6. REAL WORLD CHALLENGES AND FUTURE PERSPECTIVES
  7. CONCLUSION

Elsevier Neurocomputing

  • Double column
  • H-Index: 177
  • Country: Netherlands

Adversarial attacks and defenses in deep learning for image recognition: A survey (2022, 20)

  1. Introduction
  2. Definitions and notations
  3. Adversarial attacks
  4. Adversarial defense
  5. Discussion
  6. Conclusions

Adversarial attack and defense technologies in natural language processing: A survey (2022, 30)

  1. Introduction
  2. Textual adversarial example
  3. Textual adversarial attack
  4. Textual adversarial attack application
  5. Defense against textual adversarial attack
  6. Conclusion

Elsevier Computers & Security

  • Double column
  • H-Index: 112
  • Country: UK

A survey on adversarial attacks in computer vision: Taxonomy, visualization and future directions (2022, 17)

  1. Introduction
  2. Related work
  3. Preliminaries
  4. Exploration of adversarial attacks based on taxonomy
  5. Construction of knowledge graph
  6. Field visualization
  7. Trends and directions
  8. Conclusion

Springer Artificial Intelligence Review

  • Single column
  • H-Index: 101
  • Country: Netherlands

Adversarial example detection for DNN models: a review and experimental comparison (2022, 60)

  1. Introduction
  2. Related work
  3. Adversarial attacks and defense methods
  4. Adversarial example detection methods
  5. Experiment settings
  6. Results and discussions
  7. Challenges, future perspectives, and conclusion

MDPI Electronics

  • Single column
  • H-Index: 62
  • Country: Switzerland

Adversarial Attack and Defense Strategies of Speaker Recognition Systems: A Survey (2022, 38)

  1. Introduction
  2. Background
  3. Adversarial Attack
  4. Adversarial Defense
  5. Discussion
  6. Conclusions

Adversarial Attack and Defense: A Survey (2022, 19)

  1. Introduction
  2. Adversarial Attack
  3. Adversarial Example Defense
  4. Challenge
  5. Conclusions

Elsevier Computer Science Review

  • Double column
  • H-Index: 60
  • Country: Ireland

Defense strategies for Adversarial Machine Learning: A survey (2023, 20)

  1. Introduction
  2. Literature collection and related work
  3. Adversarial machine learning attacks
  4. Adversarial machine learning defenses
  5. Evaluation of defense methods
  6. Discussion

MDPI Future Internet

  • Single column
  • H-Index: 49
  • Switzerland

Adversarial Machine Learning Attacks against Intrusion Detection Systems: A Survey on Strategies and Defense (2023, 34)

  1. Introduction
  2. Related Surveys
  3. Intrusion Detection System Based on ML
  4. Adversarial Machine Learning
  5. Machine Learning Adversaries against IDS
  6. Benchmark Datasets
  7. Defense Strategies
  8. Challenges and Future Directions
  9. Conclusions
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment