Active Learning Under Malicious Mislabeling and Poisoning Attacks.
Jing LinRyan LuleyKaiqi XiongPublished in: GLOBECOM (2021)
Keyphrases
- active learning
- malicious users
- malicious attacks
- detect malicious
- detecting malicious
- malicious behavior
- insider attacks
- malicious code
- malicious activities
- insider threat
- learning strategies
- selective sampling
- machine learning
- semi fragile watermarking
- countermeasures
- pool based active learning
- training set
- normal traffic
- security threats
- learning algorithm
- network traffic
- transfer learning
- malicious nodes
- training examples
- malicious traffic
- relevance feedback
- active learning strategies
- labeled data
- data sets
- website
- learning process
- random sampling
- identity theft
- intrusion detection system
- traffic analysis
- watermarking algorithm
- online social networks