ATLAS and D3FEND
ATT&CK covers attacks on hosts, networks, identities, and cloud services. MITRE ATLAS lists attacks on AI systems, and MITRE D3FEND names the defenses that counter ATT&CK techniques. This page says how the framework uses each, and where its copy of their data differs from the source.
On this page
ATLAS
ATLAS 2026.09 lists 16 tactics, 120 techniques, 88 sub-techniques, 40 mitigations, and 73 case studies. Of the case studies, 23 are incidents against deployed AI systems and 50 are exercises by red teams and researchers. ATLAS adopted 44 of its 208 techniques and sub-techniques from ATT&CK and names the ATT&CK technique each came from, as with Exploit Public-Facing Application. The rest are specific to AI, such as prompt injection, jailbreaks, and poisoned training data.
ATLAS lists no log sources and no analytics, so the coverage map can't score its techniques the way it scores ATT&CK's. A score.yml accepts an ATLAS id such as AML.T0051 beside its ATT&CK ids. The kit's lint checks it against the pinned ATLAS release, so a detection for an AI system enters the backlog like any other.
Collect the model's telemetry first
Of the 40 ATLAS mitigations, 5 detect an attack in progress: Predictive AI Adversarial Input Detection (AML.M0015), AI Telemetry Logging (AML.M0024), Deepfake Detection (AML.M0034), AI Agent Scope Drift Detection (AML.M0038), AI Honeypots (AML.M0039). The other 35 prevent, harden, or limit. ATLAS files its mitigations as policy or technical controls, so this split by what each one does is this site's reading. AI Telemetry Logging records the inputs and outputs of a deployed model, and 18 techniques name it. A detection for prompt injection, or for exfiltration through an inference API or an agent's tools, has nothing to read without that log. Treat it like any other log source: give it a row in inventory.csv and a silence alert under DET-0000.
ATT&CK's own AI techniques
ATT&CK 20.1 has 7 techniques of its own for AI: Direct Prompt Injection (T1699), Indirect Prompt Injection (T1698), AI-Enabled Exfiltration (T1700), Impair Autonomous Defenses (T1685.007), AI Result Poisoning (T1608.007), Query Public AI Services (T1682), and Artificial Intelligence (T1588.007). The coverage map scores them like any other technique. ATT&CK names log sources for T1699, T1698, and T1700 only, so the map can't yet say which logs the others need. T1608.007, T1682, and T1588.007 are PRE techniques, so the map starts them out of scope. A detection for a technique both knowledge bases list carries both ids: the ATT&CK id counts toward coverage, and the ATLAS id ties it to ATLAS's case studies and mitigations.
Techniques ATLAS ties to a mitigation that detects
48 of the 208 techniques and sub-techniques name at least one detecting mitigation. The techniques with the most ATLAS case studies come first.
| Technique | Tactics | Mitigation that detects | Case studies | From ATT&CK |
|---|---|---|---|---|
| AML.T0053 AI Agent Tool Invocation | Execution, Privilege Escalation, Lateral Movement | AI Telemetry Logging (AML.M0024) | 19 | |
| AML.T0015 Evade AI Model | Initial Access, Defense Evasion, Impact | Predictive AI Adversarial Input Detection (AML.M0015), Deepfake Detection (AML.M0034) | 18 | |
| AML.T0051.001 LLM Prompt Injection: Indirect | Execution | AI Telemetry Logging (AML.M0024) | 18 | |
| AML.T0047 AI-Enabled Product or Service | AI Model Access | AI Telemetry Logging (AML.M0024) | 16 | |
| AML.T0093 Prompt Infiltration via Public-Facing Application | Initial Access, Persistence | AI Honeypots (AML.M0039) | 13 | |
| AML.T0051.000 LLM Prompt Injection: Direct | Execution | AI Telemetry Logging (AML.M0024) | 11 | |
| AML.T0040 AI Model Inference API Access | AI Model Access | AI Telemetry Logging (AML.M0024), AI Honeypots (AML.M0039) | 10 | |
| AML.T0086 Exfiltration via AI Agent Tool Invocation | Exfiltration | AI Telemetry Logging (AML.M0024) | 10 | |
| AML.T0000 Search Open Technical Databases | Reconnaissance | AI Honeypots (AML.M0039) | 8 | T1596 |
| AML.T0049 Exploit Public-Facing Application | Initial Access | AI Honeypots (AML.M0039) | 8 | T1190 |
| AML.T0031 Erode AI Model Integrity | Impact | Predictive AI Adversarial Input Detection (AML.M0015) | 6 | |
| AML.T0006 Active Scanning | Reconnaissance | AI Honeypots (AML.M0039) | 5 | T1595 |
| AML.T0051.002 LLM Prompt Injection: Triggered | Execution | AI Telemetry Logging (AML.M0024) | 5 | |
| AML.T0085.001 Data from AI Services: AI Agent Tools | Collection | AI Telemetry Logging (AML.M0024) | 5 | |
| AML.T0116 Autonomous Reconnaissance | Reconnaissance | AI Agent Scope Drift Detection (AML.M0038) | 4 | |
| AML.T0117 Autonomous Attack-Path Adaptation | AI Attack Adaptation | AI Agent Scope Drift Detection (AML.M0038) | 4 | |
| AML.T0043.000 Craft Adversarial Data: White-Box Optimization | AI Attack Adaptation | Predictive AI Adversarial Input Detection (AML.M0015) | 3 | |
| AML.T0043.002 Craft Adversarial Data: Black-Box Transfer | AI Attack Adaptation | Predictive AI Adversarial Input Detection (AML.M0015) | 3 | |
| AML.T0043.003 Craft Adversarial Data: Manual Modification | AI Attack Adaptation | Predictive AI Adversarial Input Detection (AML.M0015) | 3 | |
| AML.T0088 Generate Deepfakes | AI Attack Adaptation | Deepfake Detection (AML.M0034) | 3 | |
| AML.T0095 Search Open Websites/Domains | Reconnaissance | AI Honeypots (AML.M0039) | 3 | T1593 |
| AML.T0095.000 Search Open Websites/Domains: Code Repositories | Reconnaissance | AI Honeypots (AML.M0039) | 3 | T1593.003 |
| AML.T0101 Data Destruction via AI Agent Tool Invocation | Impact | AI Telemetry Logging (AML.M0024) | 3 | |
| AML.T0000.003 Search Open Technical Databases: Scan Databases | Reconnaissance | AI Honeypots (AML.M0039) | 2 | T1596.005 |
| AML.T0005.001 Create Proxy AI Model: Train Proxy via Replication | AI Attack Adaptation | AI Telemetry Logging (AML.M0024) | 2 | |
| AML.T0029 Denial of AI Service | Impact | Predictive AI Adversarial Input Detection (AML.M0015) | 2 | |
| AML.T0043.001 Craft Adversarial Data: Black-Box Optimization | AI Attack Adaptation | Predictive AI Adversarial Input Detection (AML.M0015) | 2 | |
| AML.T0052 Phishing | Initial Access, Lateral Movement | Deepfake Detection (AML.M0034) | 2 | T1566 |
| AML.T0085.000 Data from AI Services: RAG Databases | Collection | AI Telemetry Logging (AML.M0024) | 2 | |
| AML.T0006.003 Active Scanning: Probe AI Agent Trigger Channels | Reconnaissance | AI Honeypots (AML.M0039) | 1 | T1595 |
| AML.T0024.002 Exfiltration via AI Inference API: Extract AI Model | Exfiltration | AI Telemetry Logging (AML.M0024) | 1 | |
| AML.T0043 Craft Adversarial Data | AI Attack Adaptation | Predictive AI Adversarial Input Detection (AML.M0015) | 1 | |
| AML.T0043.004 Craft Adversarial Data: Insert Backdoor Trigger | AI Attack Adaptation | Predictive AI Adversarial Input Detection (AML.M0015) | 1 | |
| AML.T0051 LLM Prompt Injection | Execution | AI Telemetry Logging (AML.M0024) | 1 | |
| AML.T0052.000 Phishing: Spearphishing via Social Engineering LLM | Initial Access, Lateral Movement | Deepfake Detection (AML.M0034) | 1 | |
| AML.T0084 Discover AI Agent Configuration | Discovery | AI Honeypots (AML.M0039) | 1 | |
| AML.T0114 AI Service Web Interface | Command and Control | AI Telemetry Logging (AML.M0024) | 1 | |
| AML.T0124 Autonomous Attack Orchestration | AI Attack Adaptation | AI Agent Scope Drift Detection (AML.M0038) | 1 | |
| AML.T0132 Misconfigured or Publicly Exposed AI Services | Initial Access | AI Honeypots (AML.M0039) | 1 | |
| AML.T0006.000 Active Scanning: Enumerate Hosted AI Resources | Reconnaissance | AI Honeypots (AML.M0039) | 0 | |
| AML.T0006.001 Active Scanning: Query Platform Metadata APIs | Reconnaissance | AI Honeypots (AML.M0039) | 0 | |
| AML.T0006.002 Active Scanning: Scan for Exposed AI Infrastructure | Reconnaissance | AI Honeypots (AML.M0039) | 0 | T1595 |
| AML.T0024 Exfiltration via AI Inference API | Exfiltration | AI Telemetry Logging (AML.M0024) | 0 | |
| AML.T0024.000 Exfiltration via AI Inference API: Infer Training Data Membership | Exfiltration | AI Telemetry Logging (AML.M0024) | 0 | |
| AML.T0024.001 Exfiltration via AI Inference API: Invert AI Model | Exfiltration | AI Telemetry Logging (AML.M0024) | 0 | |
| AML.T0052.001 Phishing: Deepfake-Assisted Phishing | Initial Access, Lateral Movement | Deepfake Detection (AML.M0034) | 0 | |
| AML.T0085 Data from AI Services | Collection | AI Telemetry Logging (AML.M0024) | 0 | |
| AML.T0133 Discover AI Agent Runtime Capabilities | Discovery | AI Honeypots (AML.M0039) | 0 |
D3FEND
D3FEND links an attack to a defense through a digital artifact. The attack technique accesses, creates, or modifies an artifact such as a process, a file, or a network flow, and a defensive technique analyzes or hardens the same artifact. D3FEND 1.6.0 links 392 Enterprise and ICS technique ids to 156 defensive techniques: 56 detect, 32 harden, 29 isolate, 14 evict, 12 model, 9 restore, 4 deceive. Once the ids ATT&CK has revoked move to their replacements, 387 of them are techniques in ATT&CK 20.1. A detection program reads the Detect techniques, because each one is a named kind of analysis a hypothesis can start from.
In the coverage map, a technique's detail lists the Detect techniques D3FEND links to it, grouped by the artifact they analyze, and counts the rest by tactic. A parent technique counts its sub-techniques' links and a sub-technique counts its parent's, which is how D3FEND's own site shows them, and each link that comes through another id says which. Mobile techniques have no D3FEND links.
Two examples
For T1003.001, LSASS Memory, the map shows 12 defensive techniques, and 3 of them detect:
| Detect technique | Artifact it analyzes | Linked through |
|---|---|---|
| D3-PLA Process Lineage Analysis | Process | the technique itself |
| D3-PSMD Process Self-Modification Detection | Process | the technique itself |
| D3-PSA Process Spawn Analysis | Process | the technique itself |
For T1558.003, Kerberoasting, D3FEND links the sub-technique itself to 10 defensive techniques, all through Network Traffic and RPC Network Traffic. The parent, T1558, adds links through Access Token and Credential, for 21 defensive techniques in all, and 10 of them detect:
| Detect technique | Artifact it analyzes | Linked through |
|---|---|---|
| D3-APCA Application Protocol Command Analysis | Network Traffic | the technique itself |
| D3-CSPP Client-server Payload Profiling | Network Traffic | the technique itself |
| D3-NTCD Network Traffic Community Deviation | Network Traffic | the technique itself |
| D3-NTSA Network Traffic Signature Analysis | Network Traffic | the technique itself |
| D3-PHDURA Per Host Download-Upload Ratio Analysis | Network Traffic | the technique itself |
| D3-PMAD Protocol Metadata Anomaly Detection | Network Traffic | the technique itself |
| D3-RTSD Remote Terminal Session Detection | Network Traffic | the technique itself |
| D3-UGLPA User Geolocation Logon Pattern Analysis | Network Traffic | the technique itself |
| D3-CCSA Credential Compromise Scope Analysis | Credential | T1558 |
| D3-RTA RPC Traffic Analysis | RPC Network Traffic | the technique itself |
Differences from D3FEND's own data
The extract reads D3FEND's bulk mappings file, which lists each technique's links on its own, and the coverage map folds parents and sub-techniques when it shows one. On 2026-10-20 the folded counts matched D3FEND's API for 5 of the 5 techniques checked; the outside checks page has the numbers.
D3FEND 1.6.0 maps to ATT&CK 19.0, and this site pins 20.1. ATT&CK has since revoked 22 of the ids D3FEND maps. The extract moves their links to the technique ATT&CK names as each one's replacement, such as T1562.001 to T1685 and T1574.002 to T1574.001. 3 more, T0807, T0853, T1053.004, have no current technique, so the map never shows them. Techniques ATT&CK added after 19.0 have no D3FEND links yet. Of ATT&CK's 7 AI techniques, none has a D3FEND link.
Pinning and updating
tools/atlas_extract.py and tools/d3fend_extract.py each read one pinned release and write atlas-2026.09.json and d3fend-1.6.0.json. Rerun them on each release and review the diff, then rerun tools/d3fend_extract.py --check. In the kit, python tools/attack_pin.py pins the ATLAS ids with ATT&CK's in the technique list lint checks against, and --atlas-only re-pins ATLAS alone.
Licenses
MITRE ATLAS data, copyright The MITRE Corporation, licensed under the Apache License 2.0. Content ATLAS adopts from ATT&CK is also subject to the ATT&CK terms of use. MITRE D3FEND data, copyright The MITRE Corporation, licensed under the MIT License and the D3FEND terms of use, which ask that copies keep this notice. The extracts carry these notices, and this site's CC BY-NC license does not cover them.