Option Profile Creation 

You can create a new option profile to define the scan settings and detection scope for model scans. 

To create an option profile : 

1. Navigate to Configuration > Option Profile tab and click New Option Profile. 
2. Enter the values in the Basic Details page. 
3. Configure Scan Settings for the model scan.
4. Configure Search Criteria to define the scope of detection. 
5. Click Create Option Profile.

Once the option profile is created, it is listed in the Option Profiles tab. You can select this option profile while creating or editing a model. 

Steps to Create an Option Profile

Basic Details 

Enter name for the option profile and add tags to be associated with the option profile. 

You can also define the option profile as the default option profile for the subscription. 

Scan Settings 

Configure the scan settings for the model scan.  

• Temperature
• Top K
• Maximum Tokens
• Top P
• Repetition Penalty
• Response Timeout
• Retry Attempts
• Parallelism

For details of the scan setting fields, see Scan Settings.

Search Criteria

Select a value from the Detection Scope to define which detections should be checked during the model scanning. whether the scan checks for vulnerabilities in our Knowledge Base.

You can select one of the following values:

• All Detections: If selected, the Attack List displays all the available detection options.
• Denial Of Service: If selected, the Attack List displays methods to detect attacks aimed at making a service unavailable to its intended users.
• Encoding Attack: If selected, the Attack List displays methods to detect attacks that use encoded inputs to bypass the model's safety filters.
• Hallucination: If selected, the Attack List displays methods to detect instances where the model generates false or misleading information.
• Jailbreak and Prompt Injection Attacks: If selected, the Attack List displays jailbreak methods you can select. 
• Malaction: If selected, the Attack List displays methods to detect instances where the model is manipulated into performing harmful or unintended actions.
• Misinformation: If selected, the Attack List displays methods to detect instances where the model produces or amplifies false, misleading, or unverified content.
• Pretext: If selected, the Attack List displays methods to detect attempts where a fabricated scenario or false context is used to manipulate the model into revealing restricted information or behaving inappropriately.
• Risk Categories: If selected, the Attack List displays the Knowledge Base option to be included in the detection scope.
• Sensitive Information Disclosure: If selected, the Attack List displays methods to detect instances where sensitive information is exposed.

Comments

Enter comments to be associated with the option profile that is created. 

Confirmation

Review the settings defined for the model and then click Create Option Profile.