Palo Alto Networks, Inc.

Stefan Achleitner

Shengming Xu

Yu Fu

Lei Xu

Chengcheng Xu

Yanhui Jia

Taojie Wang

Hui Gao

Matthew W Tennis

Bo Qu

Ajaya Neupane

Jin Chen

Zhibin Zhang

Yuwen Dai

An inline malicious traffic detector captures handshake messages in a session with a security protocol. The inline malicious traffic detector comprises a classifier that generates a verdict for the session indicating malicious or benign. The classifier is trained on labelled sessions using custom features generated from handshake messages. Based on determining that the session is malicious using features of the handshake messages, the inline malicious traffic detector blocks the session.

Inline detection of encrypted malicious network sessions

The present application discloses a method, system, and computer system for detecting malicious SQL or command injection strings. The method includes obtaining an SQL or command injection string and determining whether the command injection string is malicious based at least in part on a machine learning model.

Network attack detection with targeted feature extraction from exploit tools

Detection of command and control malware is disclosed. A network traffic session is monitored. Automatic feature identification for real-time malicious command and control traffic detection based on a request header of the monitored network traffic session using a deep learning model is performed.

Deep learning pipeline to detect malicious command and control traffic

Techniques for sample traffic based self-learning malware detection are disclosed. In some embodiments, a system/process/computer program product for sample traffic based self-learning malware detection includes receiving a plurality of samples for malware detection analysis using a sandbox; executing each of the plurality of samples in the sandbox and monitoring network traffic during execution of each of the plurality of samples in the sandbox; detecting that one or more of the plurality of samples is malware based on automated analysis of the monitored network traffic using a command and control (C2) machine learning (ML) model if there is not a prior match with an intrusion prevention system (LPS) signature; and performing an action in response to detecting that the one or more of the plurality of samples is malware based on the automated analysis of the monitored network traffic using the C2 ML model. In some embodiments, the IPS signatures and C2 ML model are automatically generated and trained.

Sample traffic based self-learning malware detection

An anomaly detection model is trained to detect malicious traffic sessions with a low rate of false positives. A sample feature extractor extracts tokens corresponding to human-readable substrings of incoming unstructured payloads in a traffic session. The tokens are correlated with a list of malicious traffic features and frequent malicious traffic features across the traffic session are aggregated into a feature vector of malicious traffic feature frequencies. An anomaly detection model trained on feature vectors for unstructured malicious traffic samples predicts the traffic session as malicious or unclassified. The anomaly detection model is trained and updated based on its' ongoing false positive rate and malicious traffic features in the list of malicious traffic features that result in a high false positive rate are removed.

Malicious traffic detection with anomaly detection modeling

Application-initiated network traffic is intercepted and analyzed by an application firewall in order to identify streams of traffic for a target application. An application signature generator preprocesses the raw data packets from the intercepted network traffic by tokenizing the data packets and then weighting each token according to its importance for application identification. The weighted features for each data packet are clustered using an unsupervised learning model, and the resulting clusters are iteratively refined and re-clustered using a proximity score between the clusters and feature vectors for key tokens for the target application. The application signature generator generates a signature for the clusters corresponding to the target application which the application firewall implements for filtering network traffic.

Label guided unsupervised learning based network-level application signature generation

Techniques for sample traffic based self-learning malware detection are disclosed. In some embodiments, a system/process/computer program product for sample traffic based self-learning malware detection includes receiving a plurality of samples for malware detection analysis using a sandbox; executing each of the plurality of samples in the sandbox and monitoring network traffic during execution of each of the plurality of samples in the sandbox; detecting that one or more of the plurality of samples is malware based on automated analysis of the monitored network traffic using a command and control (C2) machine learning (ML) model if there is not a prior match with an intrusion prevention system (IPS) signature; and performing an action in response to detecting that the one or more of the plurality of samples is malware based on the automated analysis of the monitored network traffic using the C2 ML model. In some embodiments, the IPS signatures and C2 ML model are automatically generated and trained.

Growing community of inventors

San Jose, CA, United States of America

Stefan Achleitner