Investigate Threat Logs and AI Security Logs: Log Viewer

• Log in to Strata Cloud Manager.
• Select Incidents and Alerts → Log Viewer.
• View the logs under Firewall/Threat logs and Firewall/AI Security.
  You can view the AI security logs using either Firewall/Threat logs or Firewall/AI Security logs, depending on your use of Strata Logging Service (SLS) for log forwarding.

• Without Strata Logging Service (SLS) - Threat Logs
• With Strata Logging Service (SLS) - AI Security Logs

Without Strata Logging Service (SLS) - Threat Logs

View security threat logs without Strata Logging Service (SLS).

Use Firewall/Threat logs with subtype 'ai-security' for comprehensive AI Runtime Security threat detection and analysis when using Panorama without SLS.

Where Can I Use This?	What Do I Need?
AI Runtime Security Log Inspection	Deploy AI Runtime Security: Network Intercept for Panorama Managed Firewall

• Log in to Strata Cloud Manager.
• Select Incidents and Alerts → Log Viewer.
• Select Firewall/Threat logs with subtype "ai-security".

• Panorama supports “Threat” logs with the subtype ‘ai-security' to log threats triggered by the AI security profile.
• The ' Threat Category ' column identifies specific AI Runtime Security threat types.
• Enhanced threat details include Threat IDs, which uniquely combine the threat category and model name (for example, “AI Prompt Injection: GCP - Gemini 1.5 Flash”). See the threat category types table below for more information about the specific Threat IDs, descriptions, and severities.
• Advanced filtering capabilities enable analysis of specific threat types or combinations of threats and models.
• Recommended for Panorama managed firewalls or when you don’t want to forward the logs to SLS.

Threat Category Types

The table below provides details on the various threat categories, when they are triggered, and their respective severities:

Threat CategoryIssue ID	Description	Severity	Threat ID: Name	Example Threat ID
ai-prompt-injection	Prompt injection detection	Medium	AI Prompt Injection: <Model Name>	AI Prompt Injection: GCP - Gemini 1.5 Pro
ai-url-security	URL category triggered with action Alert or Block	Low	AI URL Security: <Model Name>	AI URL Security: GCP - Gemini 1.5 Pro
ai-data-leakage	Sensitive data detected by DLP	Dependent on configurations	AI Data Leakage: <Model Name>	AI Data Leakage: GCP - Gemini 1.5 Pro
ai-model-access-control	Traffic blocked due to model access control setting	Low	AI Model Access Control: <Model Name>	AI Model Access Control: GCP - Gemini 1.5 Pro
ai-latency-block	Traffic blocked due to max latency setting	Low	AI Latency Block: <Model Name>	AI Latency Block: GCP - Gemini 1.5 Pro
ai-database-security-<query type>	Database query detected with action Alert or Block Query Type: Read, Create, Update, Delete	Read: Low Create: Medium Update: Medium Delete: High	AI Database Security <query type>: <Model Name>	AI Database Security Read: GCP - Gemini 1.5 Pro AI Database Security Create: GCP - Gemini 1.5 Pro AI Database Security Update: GCP - Gemini 1.5 Pro AI Database Security Delete: GCP - Gemini 1.5 Pro

With Strata Logging Service (SLS) - AI Security Logs

View AI security logs with Strata Logging Service (SLS).

Use Firewall/AI Security logs for detailed AI-specific threat information for enhanced AI security monitoring and analysis when using SLS for log forwarding.

The AI security logs provide more information as compared to the threat logs.

Where Can I Use This?	What Do I Need?
AI Runtime Security Log Inspection	Deploy AI Runtime Security: Network Intercept for Panorama Managed Firewall

• Log in to Strata Cloud Manager.
• Select Incidents and Alerts → Log Viewer.
• Select Firewall/AI Security.

The AI security logs:

• SLS generates the AI security logs when AI security threats are detected between AI applications and AI models.
• Includes detailed threat snippet identification and reporting.
• Provide in-depth threat information and reports for different protection types such as AI model protection, AI application protection, and AI data protection.
  Create an AI security profile and attach a model group with specific protections to monitor traffic between your AI models, AI applications, and AI data and detect threats.
• Recommended for platforms with SLS for log forwarding and if you want detailed AI-specific threat information.

A log is generated for each AI security threat detected between an AI application and model. The logs are generated for prompt injections, sensitive data leakage, malicious URLs detected, and AI-generated database queries.

Traffic Details

Click on a log to view the detailed traffic logs showing general information about the AI Runtime Security. The traffic details logs include:

• The AI model name, AI model CSP region name, AI incident type, AI incident subtype, AI security profile name, and an incident report ID for troubleshooting.
• The logs also include the session ID, source, and destination details.

The AI security threats are categorized into AI Incident types and subtypes:

Incident Type	Incident Subtype	Incident Subtype Details
ai-model-protection	prompt-injection	NA
ai-app-protection	url-security	URL categories detected
ai-data-protection	data-rule database-security	Data Rule: Name of DLP profile triggered Database Security: type of database query detected (Create, Read, Update, or Delete)
model-denied		N/A
latency-block		N/A

AI Security Report

The AI Security Report tab provides detailed information on the AI traffic and specific AI threat logs. It includes threat snippet identification and reporting. The AI Runtime Security system supports asynchronous identification of particular content snippets that trigger security detectors.

Each report includes a unique report ID to help debug logs.

1. Model Protection:
   The model protection report displays logs for any detected prompt injection threats. The prompt injection snippet (at most 1000 characters) helps identify the trigger and can include multiple snippets for complex payloads.

2. Application Protection:
   The application protection report shows URL categories and the specific URLs in the payload that triggered these categories

3. Data Protection
   The data protection report lists DLP data patterns that were triggered and the masked content that caused each pattern to trigger. These logs are categorized based on low, medium, and high-severity alerts. The data protection report includes two main components:

   • Matched Data Patterns (DLP):
     • Shows matched Data Loss Prevention (DLP) data patterns that were triggered.
     • Display specific snippets of content matching DLP data patterns. Content is stored and masked based on Manage → Data Loss Prevention → Settings → Sensitive Data configuration.
     • Data pattern matches are categorized based on low, medium, and high Confidence Level.

   • Database Security:
     • Shows content containing flagged AI-generated SQL database queries.
     • If multiple SQL queries are detected in the model response, the report shows up to 10 SQL queries (each up to 1,000 characters), prioritized in the following order: Delete, Update, Create, and Read action.