ATLAS Matrix
AI Attack Tactics
Comprehensive framework for understanding and defending against AI-specific attack tactics and techniques. Based on MITRE ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems).
ATLAS Attack Matrix
The ATLAS Matrix shows the progression of tactics used in attacks against AI systems, with specific techniques for each tactic. Click on any tactic to explore its techniques.
Reconnaissance
The adversary is trying to gather information they can use to plan future operations.
Resource Development
The adversary is trying to establish resources they can use to support operations.
Initial Access
The adversary is trying to get into your AI system.
AI Model Access
The adversary is trying to gain access to AI models and their capabilities.
Discovery
The adversary is trying to figure out your AI environment.
AI Attack Staging
The adversary is trying to prepare for AI-specific attacks.
Execution
The adversary is trying to run malicious code on your AI system.
Persistence
The adversary is trying to maintain their foothold in your AI system.
Privilege Escalation
The adversary is trying to gain higher-level permissions in your AI system.
Defense Evasion
The adversary is trying to avoid being detected in your AI system.
Credential Access
The adversary is trying to steal account names and passwords from your AI system.
Collection
The adversary is trying to gather data of interest from your AI system.
Command and Control
The adversary is trying to communicate with compromised AI systems.
Exfiltration
The adversary is trying to steal data from your AI system.
Impact
The adversary is trying to manipulate, interrupt, or destroy your AI system.
Key ATLAS Features
AI-Specific
Techniques specifically designed for AI/ML systems, not adapted from traditional cybersecurity
MITRE Compatible
Follows the same structure as MITRE ATT&CK, making it familiar to security professionals
Defense Focused
Each technique includes specific mitigations and defense strategies