Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples.
Guanhong TaoShiqing MaYingqi LiuXiangyu ZhangPublished in: NeurIPS (2018)
Keyphrases
- data sets
- false positives
- detection algorithm
- detection accuracy
- automatic detection
- detection rate
- attack detection
- object detection
- false alarms
- anomaly detection
- attribute values
- normal traffic
- computer vision
- traffic analysis
- network attacks
- denial of service attacks
- detect malicious
- data samples
- rule base
- face detection
- detection method
- training samples
- neural network