Towards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothing.
Daniel GibertGiulio ZizzoQuan LePublished in: CoRR (2023)
Keyphrases
- deep learning
- unsupervised learning
- unsupervised feature learning
- detect malicious
- machine learning
- mental models
- malicious code
- network security
- pattern recognition
- ddos attacks
- deep architectures
- feature extraction
- object detection
- intrusion detection
- weakly supervised
- defense mechanisms
- detecting malicious
- learning strategies
- pairwise
- information retrieval