Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
Explore this paper's citation graph
Summary
This tutorial introduces the fundamentals of adversarial machine learning to the security community, and presents novel techniques that have been recently proposed to assess performance of pattern classifiers and deep learning algorithms under attack, evaluate their vulnerabilities, and implement defense strategies that make learning algorithms more robust to attacks.
- Type
- article
- Published
- 2017-12-08
- Cited by
- 1,733
- References
- 132
- Access
- Open access
- OpenAlex
- https://openalex.org/W2773446523
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:53107276
Keywords
Adversarial system, Machine learning, Artificial intelligence, Computer science, Adversarial machine learning
References
- Good Word Attacks on Statistical Spam Filters
- Statistical Meta-Analysis of Presentation Attacks for Secure Multibiometric Systems
- On Robustness and Regularization of Structural Support Vector Machines
- On Attacking Statistical Spam Filters
- Adversarial Biometric Recognition : A review on biometric system security from the adversarial machine-learning perspective
- Intriguing properties of neural networks
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
- Mining adversarial patterns via regularized loss minimization
- A survey of image spamming and filtering techniques
- Machine learning in adversarial environments
- On the vulnerability of face verification systems to hill-climbing attacks
- ANTIDOTE: understanding and defending against poisoning of anomaly detectors
- Pattern Recognition Systems under Attack: Design Issues and Research Challenges
- Adversarial attacks against intrusion detection systems: Taxonomy, solutions and open issues
- A unifying view on dataset shift in classification
- Synthetic handwritten CAPTCHAs
- Practical Evasion of a Learning-Based Classifier: A Case Study
- Multiple classifier systems for robust classifier design in adversarial environments
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
- Malicious PDF detection using metadata and structural features
Cited by
- Adversarial Detection of Flash Malware: Limitations and Open Issues
- Hardening quantum machine learning against adversaries
- A Learning and Masking Approach to Secure Learning
- When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time
- Adversarial Generative Nets: Neural Network Attacks on State-of-the-Art Face Recognition
- Adversarial Deep Learning for Robust Detection of Binary Encoded Malware
- Adversarial Perturbation Intensity Achieving Chosen Intra-Technique Transferability Level for Logistic Regression
- Adversarial classification: An adversarial risk analysis approach
- Attack Strength vs. Detectability Dilemma in Adversarial Machine Learning
- Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables
- Explaining Black-box Android Malware Detection
- Adversarial Attacks Against Medical Deep Learning Systems
- PRADA: Protecting Against DNN Model Stealing Attacks
- POTs: The revolution will not be optimized?
- There Is No Free Lunch In Adversarial Robustness (But There Are Unexpected Benefits)
- Built-in Vulnerabilities to Imperceptible Adversarial Perturbations
- Adaptive Adversarial Attack on Scene Text Recognition
- Motivating the Rules of the Game for Adversarial Example Research
- POTs: protective optimization technologies
- Maschinelles Lernen und künstliche Intelligenz in der Informationssicherheit