Poisoning Attacks against Support Vector Machines
Explore this paper's citation graph
Summary
It is demonstrated that an intelligent adversary can, to some extent, predict the change of the SVM's decision function due to malicious input and use this ability to construct malicious data.
- Type
- preprint
- Published
- 2012-06-26
- Cited by
- 1,883
- References
- 23
- Access
- Open access
- OpenAlex
- https://openalex.org/W2112507308
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:9089716
Keywords
Support vector machine, Computer science, Classifier (UML), Artificial intelligence, Construct (python library)
References
- ZOZZLE: Fast and Precise In-Browser JavaScript Malware Detection
- Statistical fraud detection: A review
- SpamBayes: Effective open-source, Bayesian based, email classification system
- Comparison of learning algorithms for handwritten digit recognition
- Detection and analysis of drive-by-download attacks and malicious JavaScript code
- Static detection of malicious JavaScript-bearing PDF documents
- ANTIDOTE: understanding and defending against poisoning of anomaly detectors
- Multiple classifier systems for robust classifier design in adversarial environments
- Nash Equilibria of Static Prediction Games
- Incremental and Decremental Support Vector Machine Learning
- Nightmare at test time: robust learning by feature deletion
- The security of machine learning
- Convex Learning with Invariances
- Can machine learning be secure?
- Exploiting Machine Learning to Subvert Your Spam Filter
- Learning to classify with missing and corrupted features
- A sense of self for Unix processes
- Online Anomaly Detection under Adversarial Impact
- The Handbook of Matrices
- Forschungsberichte der Fakultät IV – Elektrotechnik und Informatik C UJO : Efficient Detection and Prevention of Drive-by-Download Attacks
Cited by
- Detecting Malware with Information Complexity
- The Security of Latent Dirichlet Allocation
- Evaluating model drift in machine learning algorithms
- Towards Making Systems Forget with Machine Unlearning
- Trusted computation with an adversarial cloud
- Visualizing Object Detection Features
- Mitigating Mimicry Attacks Against the Session Initiation Protocol
- Analysis of classifiers’ robustness to adversarial perturbations
- Man vs. Machine: Practical Adversarial Detection of Malicious Crowdsourcing Workers
- L-GEM based robust learning against poisoning attack
- Systematic Poisoning Attacks on and Defenses for Machine Learning in Healthcare
- On the Practicality of Integrity Attacks on Document-Level Sentiment Analysis
- Causative attack to Incremental Support Vector Machine
- Security and privacy in business networking
- AMAL: High-fidelity, behavior-based automated malware analysis and classification
- Adding Robustness to Support Vector Machines Against Adversarial Reverse Engineering
- Better Malware Ground Truth: Techniques for Weighting Anti-Virus Vendor Labels
- Lux0R: Detection of Malicious PDF-embedded JavaScript code through Discriminant Analysis of API References
- Pattern Recognition Systems under Attack: Design Issues and Research Challenges
- Automated Attacks on Compression-Based Classifiers
Related papers
- [발표논문] 인공신경망과 Support Vector Machine의 기업부도예측 성과 비교-Support Vector Machine의 유용성을 중심으로-
- Linear Classification of data with Support Vector Machines and Generalized Support Vector Machines
- Pre-extracting support vectors for support vector machine
- A comparison among four SVM classification methods: LSVM, NLSVM, SSVM and NSVM
- Incremental Vector Support Vector Machine Learning Algorithm
- Network intrusion detection method by least squares support vector machine classifier
- Prediction of Data Classification Based on Support Vector Machine