# US 2014/0297572 A1 · Method and system for classifying a protocol message in a data communication network

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2014/0297572 A1
- Document ID: US20140297572A1
- Status: Published application
- Kind: A1
- Application number: 14/234,669
- Filed: 2012-07-26
- Published: 2014-10-02
- Earliest claimed: 2011-07-26
- Assignees: Security Matters Ltd.
- Inventors: Emmanuele Zambon
- Web page: https://patentgrep.com/patent/US20140297572A1

## CPC

- G06N 20/00: Machine learning
- G06F 21/50: Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- H04L 43/18: Protocol analysers
- H04L 63/0245: {Filtering by information in the payload}
- H04L 63/14: {for detecting or protecting against malicious traffic}
- H04L 63/1416: {Event detection, e.g. attack signature detection}
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- H04L 67/02: based on web technology, e.g. hypertext transfer protocol [HTTP]
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

An intrusion detection method for detecting an intrusion in data traffic on a data communication network parses the data traffic to extract at least one protocol field of a protocol message of the data traffic, and associates the extracted protocol field with a model for that protocol field. The model is selected from a set of models. An assessment is made to determine if a contents of the extracted protocol field is in a safe region as defined by the model, and an intrusion detection signal is generated in case it is established that the contents of the extracted protocol field is outside the safe region. The set of models may comprise a corresponding model for each protocol field of a set of protocol fields.

## Claims

### Claim 1

An intrusion detection method for detecting an intrusion in data traffic on a data communication network, the method comprising:
parsing the data traffic to extract at least one protocol field of a protocol message of the data traffic;
associating the extracted protocol field with a respective model for that protocol field, the model being selected from a set of models;
assessing if a contents of the extracted protocol field is in a safe region as defined by the model; and
generating an intrusion detection signal in case it is established that the contents of the extracted protocol field is outside the safe region,
wherein a plurality of model types are provided,
wherein a model type for the extracted protocol field is selected from the plurality of model types on the basis of a characteristic of the extracted protocol field, and wherein the model for the extracted protocol field is built on the basis of the selected model type.

### Claim 2 (depends on 1)

The intrusion detection method according to claim 1, wherein the set of models comprises a model for an operator protocol field and a model for an argument protocol field, the associating and assessing being performed for the operator protocol field and the argument protocol field.

### Claim 3 (depends on 2)

The intrusion detection method according to claim 2, wherein the set of models furthermore comprises a model for a marshalling protocol field, the associating and assessing furthermore being performed for the marshalling protocol field.

### Claim 4

(canceled)

### Claim 5 (depends on 1)

The intrusion detection method according to claim 1, wherein the characteristic of the protocol field comprises a data type of the protocol field, the method comprising:
determining a data type of the extracted protocol field, and
selecting the model type using the determined data type.

### Claim 6 (depends on 1)

The intrusion detection method according to claim 1, wherein the characteristic of the protocol field comprises a semantic of the protocol field, the method comprising:
determining a semantic of the extracted protocol field, and
selecting the model type using the determined semantic.

### Claim 7 (depends on 1)

The intrusion detection method according to claim 1, wherein the set of models comprises a respective model for each protocol field of the set of protocol fields.

### Claim 8 (depends on 1)

The intrusion detection method according to claim 1, wherein the model for the field is determined in a learning phase, the learning phase comprising:
parsing the data traffic to extract at least one protocol field of the protocol applied in the data traffic;
associating the extracted protocol field with the model for that protocol field, the model being selected from the set of models and
updating the model for the extracted protocol field using a contents of the extracted protocol field.

### Claim 9 (depends on 8)

The intrusion detection method according to claim 8, wherein if no association can be made between the extracted protocol field and one of the models,
creating a new model for the extracted protocol field and adding the new model to the set of models.

### Claim 10 (depends on 1)

The intrusion detection method according to claim 1, wherein the intrusion detection signal is further generated when the parsing cannot establish the field as complying with the protocol.

### Claim 11 (depends on 1)

The intrusion detection method according to claim 1, wherein the intrusion detection signal is further generated when the extracted field cannot be associated with any of the models of the set of models.

### Claim 12 (depends on 1)

The intrusion detection method according to claim 1, wherein the protocol is at least one of an application layer protocol, a session layer protocol, a transport layer protocol or a lower level protocol stack protocol.

### Claim 13 (depends on 1)

The intrusion detection method according to claim 1, wherein the method further comprises, in response to generating the intrusion detection signal, at least one of:
removing the protocol field or a data packet containing the protocol field; and
raising and outputting an intrusion alert message.

### Claim 14 (depends on 1)

The intrusion detection method according to claim 1, wherein the model for the protocol field comprises at least one of
a set of acceptable protocol field values,
a numeric distribution of protocol field values; and
a definition of a range of acceptable protocol field values.

### Claim 15 (depends on 1)

The intrusion detection method according to claim 1, wherein the model for the protocol field comprises
a definition of acceptable letters, digits, symbols, and scripts.

### Claim 16 (depends on 1)

The intrusion detection method according to claim 1, wherein the model for the protocol field comprises a set of predefined intrusion signatures.

### Claim 17 (depends on 1)

The intrusion detection method according to claim 1, wherein the set of models comprises two models for one protocol field, a specific one of the two models being associated with the one protocol field based on the value of another protocol field.

### Claim 18

An intrusion detection system for detecting an intrusion in data traffic on a data communication network, the system comprising:
a parser for parsing the data traffic to extract at least one protocol field of a protocol message of the data traffic;
an engine for associating the extracted protocol field with a respective model for that protocol field, the model being selected from a set of models;
a model handler for assessing if a contents of the extracted protocol field is in a safe region as defined by the model; and
an actuator for generating an intrusion detection signal in case it is established that the contents of the extracted protocol field is outside the safe region,
wherein a plurality of model types are provided,
wherein the system is arranged for selecting a model type for the extracted protocol field from the plurality of model types on the basis of a characteristic of the extracted protocol field, and for building the model for the extracted protocol field on the basis of the selected model type.

### Claim 19 (depends on 18)

The intrusion detection system according to claim 18, wherein the set of models comprises a model for an operator protocol field and a model for an argument protocol field, the engine being arranged for performing the associating and assessing for the operator protocol field and the argument protocol field.

### Claim 20 (depends on 19)

The intrusion detection system according to claim 19, wherein the set of models furthermore comprises a model for a marshalling protocol field, the engine furthermore being arranged for performing the associating and assessing for the marshalling protocol field.

### Claim 21

(canceled)

### Claim 22 (depends on 18)

The intrusion detection system according to claim 18, wherein the characteristic of the protocol field comprises a data type of the protocol field, the system being arranged for:
determining a data type of the extracted protocol field, and
selecting the model type using the determined data type.

### Claim 23 (depends on 18)

The intrusion detection system according to claim 18, wherein the characteristic of the protocol field comprises a semantic of the protocol field, the system being arranged for:
determining a semantic of the extracted protocol field, and
selecting the model type using the determined semantic.

### Claim 24 (depends on 18)

The intrusion detection system according to claim 18, wherein the set of models comprises a respective model for each protocol field of a set of protocol fields.

### Claim 25 (depends on 18)

The intrusion detection system according to claim 18, further arranged to be operated in a learning phase, the learning phase for learning at least one of the models, the model handler being arranged for updating in the learning phase the model for the extracted protocol field using a contents of the extracted protocol field.

### Claim 26 (depends on 25)

The intrusion detection system according to claim 25, wherein the engine is further arranged to in the learning phase, if no association can be made between the extracted protocol field and one of the models, creating a new model for the extracted protocol field and add the new model to the set of models.

### Claim 27 (depends on 18)

The intrusion detection system according to claim 18, wherein the actuator is further arranged to generate the intrusion detection signal in response to an indication from the parser that the parser cannot establish the field as complying to the protocol.

### Claim 28 (depends on 18)

The intrusion detection system according to claim 18, wherein the actuator is further arranged to generate the intrusion detection signal in response to an indication from the engine that the extracted field cannot be associated with any of the models of the set of models.

### Claim 29 (depends on 18)

The intrusion detection system according to claim 18, wherein the protocol is at least one of an application layer protocol, a session layer protocol, a transport layer protocol or a lower level protocol stack protocol.

### Claim 30 (depends on 18)

The intrusion detection system according to claim 18, wherein the actuator is arranged to, in response to the generation of the intrusion detection signal:
removing the protocol field or a data packet containing the protocol field; and
raising and outputting an intrusion alert message.

### Claim 31 (depends on 18)

The intrusion detection system according to claim 18, wherein the model for the protocol field comprises at least one of
a set of acceptable protocol field values,
a numeric distribution of protocol field values; and
a definition of a range of acceptable protocol field values.

### Claim 32 (depends on 18)

The intrusion detection system according to claim 18, wherein the model for the protocol field comprises:
a definition of acceptable letters, digits, symbols, and scripts.

### Claim 33 (depends on 18)

The intrusion detection system according to claim 18, wherein the model for the protocol field comprises a set of predefined intrusion signatures.

### Claim 34 (depends on 18)

The intrusion detection system according to claim 18, wherein the set of models comprises two models for one protocol field, the engine being arranged for associating a specific one of the two models with the one protocol field based on the value of another protocol field.
