Basic Concept: Threat modeling for AI systems requires a framework specifically designed to address AI- specific attack techniques, tactics, and procedures. General cybersecurity or governance frameworks do not capture the unique adversarial attack surface of AI and ML systems. CompTIA SecAI+ Exam Objectives identify MITRE ATLAS as the primary AI threat modeling resource.
Why B is Correct: MITRE ATLAS (Adversarial Threat Landscape for AI Systems) is specifically designed as an AI and ML threat modeling framework. It catalogs real-world adversarial tactics, techniques, and procedures targeting AI systems, enabling security architects to identify and assess threats unique to ML models such as data poisoning, model extraction, and evasion attacks. It is the industry standard for AI- specific threat modeling.
Why A is Wrong: Responsible AI is a set of ethical principles and governance guidelines for developing and deploying AI systems fairly and safely. It addresses ethics and fairness, not technical adversarial threat modeling.
Why C is Wrong: The OECD provides non-binding policy recommendations and principles for AI governance at an international level. It does not provide technical threat modeling taxonomies or AI-specific attack catalogs.
Why D is Wrong: ISO standards such as ISO 42001 establish management system requirements for AI governance. They are compliance and management frameworks, not threat modeling tools for identifying adversarial AI attack vectors.

Basic Concept: Responsible AI encompasses several key principles governing how AI systems should behave to be trustworthy and ethical. These principles are distinct but related. Understanding their precise definitions is essential for CompTIA SecAI+ Domain 4 governance questions.
Why D is Correct: Explainability in responsible AI means the AI system can clearly articulate the specific reasons, factors, and logic that led to a particular decision or output. It answers the question " why did the AI make this specific decision? " For example, an explainable credit scoring AI would not only give a score but also explain which factors such as payment history or credit utilization contributed most to that specific score.
This directly matches the question ' s description of " clearly stating reasons behind decisions. " Why A is Wrong: Accountability refers to the ability to identify who is responsible for AI system decisions and their consequences. It addresses ownership and responsibility assignment rather than explaining the reasoning behind specific decisions.
Why B is Wrong: Auditability refers to the ability to examine and verify an AI system ' s decisions, processes, and outputs through systematic review. It enables after-the-fact verification but does not mean the system itself explains its reasoning.
Why C is Wrong: Transparency refers to openness about how an AI system works at a general level, including its purpose, capabilities, limitations, and the data it was trained on. It is broader than explainability and does not specifically address articulating reasons for individual decisions.

See Explanation below for complete solution for this PBQ.
Explanation:

Basic Concept: This is a Performance-Based Question (PBQ) - a simulation item requiring interactive drag- and-drop assignment of threat categories to appropriate frameworks in the actual exam. It tests knowledge of how different AI threat frameworks categorize and address specific threat types for agentic systems.
Key Concept - Framework-to-Threat Mapping: MITRE ATLAS covers ML-specific adversarial tactics such as model evasion, data poisoning, model extraction, and prompt injection for agentic systems. OWASP LLM Top 10 addresses application-level LLM vulnerabilities such as insecure output handling, excessive agency, and supply chain risks. NIST AI RMF addresses governance-level risks across the AI lifecycle. STRIDE addresses architectural threats including spoofing, tampering, repudiation, information disclosure, DoS, and elevation of privilege.
Why This Matters: Agentic AI systems have a unique threat landscape combining traditional software vulnerabilities with AI-specific attacks. Correctly mapping threat categories to frameworks is essential for comprehensive threat modeling of systems that autonomously execute multi-step tasks with tool access and real-world consequences.
Reference: CompTIA SecAI+ Study Guide Domain 4 covers AI governance frameworks and their specific threat categories. Candidates should understand the scope and focus areas of MITRE ATLAS, OWASP LLM Top 10, NIST AI RMF, and traditional security frameworks as they apply to agentic AI system security modeling.

Basic Concept: In a layered AI system security architecture, access control must be established at each layer, beginning from the outermost point of entry. Authentication must be established at the endpoint level first, as this is the first point of interaction between users and the AI system. CompTIA SecAI+ Study Guide establishes endpoint authentication as the initial access control layer for AI systems.
Why D is Correct: Endpoint access control is the first authentication control to implement because it governs the initial connection from user devices or client applications to the AI system. All subsequent access layers including server access, model access, and data access depend on the endpoint being authenticated first.
Establishing endpoint authentication ensures that only authorized endpoints can initiate sessions and proceed through subsequent authentication layers.
Why A is Wrong: Model access controls govern who can query, update, or access the AI model ' s parameters and functions. This control layer is implemented after endpoint authentication has been established, as it applies to requests that have already been authenticated at the endpoint level.
Why B is Wrong: Server access controls manage access to the computing infrastructure hosting the AI system. While critical for infrastructure security, server-level controls are configured by administrators and are not the first authentication control for end-user access flows.
Why C is Wrong: Data access controls define what data the AI system and its users can read, write, or query.
These are implemented at a deeper layer after endpoint and potentially model authentication have verified that the requester is authorized to interact with the system at all.

Basic Concept: Class imbalance in training data - where some categories have significantly more examples than others - causes ML models to be biased toward the majority class, producing poor detection of minority class threats. Addressing this imbalance before training is critical for threat classification accuracy. CompTIA SecAI+ covers data preparation techniques under basic AI concepts.
Why B is Correct: Data augmentation addresses class imbalance by artificially increasing the number of training samples in under-represented classes. Techniques include oversampling minority classes by creating synthetic examples using methods like SMOTE (Synthetic Minority Over-sampling Technique), or undersampling majority classes. This balances label distribution and enables the model to learn decision boundaries that accurately classify all threat categories, not just the dominant ones.
Why A is Wrong: Data lineage documents the origin, movement, and transformation of data throughout its lifecycle. It provides traceability and auditability but does not address class imbalance in training data distribution.
Why C is Wrong: Data provenance records the history and context of data origins. Like lineage, it is a governance and tracking concept that does not alter data distribution for model training balance.
Why D is Wrong: Data verification confirms that data is correct and consistent with expected formats and values. It checks data quality and integrity but does not address the statistical distribution imbalance between threat classes in training datasets.