AI Security Attack Techniques

Comprehensive database of attack techniques, tactics, and procedures targeting AI systems. Explore vulnerabilities across LLMs, GenAI, Agentic AI, and MCP implementations.

Animated overview diagram of AI attack techniques across LLM, GenAI, Agentic AI and MCP

Animated overview of the AI attack techniques database, showing how LLM, GenAI, agentic AI and MCP attack clusters converge on core AI systems.

10
Total Attacks
2
Critical Severity
6
High Severity
4
Categories

Stay Updated on AI Security

Get alerts on new attack vectors and security vulnerabilities

Get weekly updates on AI security vulnerabilities and research insights.

Attack Categories

Explore Attack Categories

Browse attack techniques organized by AI system type and threat category

🤖
LLM Attacks
3 attack techniques

Large Language Model vulnerabilities including prompt injection, jailbreaking, and model manipulation techniques.

1 Critical2 High
🎨
GenAI Threats
3 attack techniques

Generative AI misuse including deepfakes, synthetic identity creation, and voice cloning attacks.

2 High
🤖
Agentic AI Attacks
2 attack techniques

Advanced threats from autonomous AI agents capable of independent exploitation and tool manipulation.

1 Critical1 High
🔗
MCP Security
2 attack techniques

Model Context Protocol vulnerabilities including server impersonation and context poisoning.

1 High
Featured Techniques

Featured Attack Techniques

Critical and high-severity attacks requiring immediate attention from security teams

Prompt Injection
CriticalLow Complexity
Critical vulnerability where malicious prompts manipulate LLM behavior to bypass safety measures.

Primary Impact:

Data ExfiltrationUnauthorized AccessSystem Manipulation
Autonomous Exploitation
CriticalHigh Complexity
AI agents that independently discover and exploit system vulnerabilities without human intervention.

Primary Impact:

System CompromiseLateral MovementData Breach
Deepfake Generation
HighMedium Complexity
Creation of synthetic media content using generative AI to impersonate individuals.

Primary Impact:

Identity TheftMisinformationSocial Engineering
Related Resources

Expand Your Knowledge

Explore frameworks, tools, and educational resources to defend against AI attacks

OWASP Top 10 LLM
Industry-standard framework for LLM security risks and vulnerabilities
Explore Framework
Attack Matrices
Comprehensive attack techniques and vectors targeting AI and ML systems across different categories
View Matrices
Security Resources
Tools, guides, frameworks, and educational materials for AI security professionals and researchers
Browse Resources

Stay Ahead of AI Threats

Our research team continuously monitors emerging AI security threats and attack techniques. Subscribe to our newsletter for the latest updates and defensive strategies.

Get Security ConsultationExplore Resources

Stay Updated on AI Security

Stay updated on new AI attack techniques and mitigation strategies

Get weekly updates on AI security vulnerabilities and research insights.

Nessus Vulnerability Scanner

Partner Solution

The industry's most widely deployed vulnerability scanner. Identify security vulnerabilities, misconfigurations, and compliance issues across your infrastructure, cloud, and container environments. Essential for AI security assessments and penetration testing.

Explore Nessus

BlackBox AI Code Generation Platform

Partner Tool

AI-powered code generation platform for developers. Generate, test, and secure AI code with advanced security features. Perfect for building secure AI applications and testing code vulnerabilities.

Try BlackBox AI