Basic Concept: ML models excel at classification tasks, learning to assign incoming data points to predefined categories based on patterns in training data. In a SOC context, alert classification is the highest-value triage function ML can perform. CompTIA SecAI+ Exam Objectives address AI-assisted security operations under Domain 3.

Why C is Correct: ML-based alert classification automatically analyzes characteristics of each alert and assigns it to a severity category such as critical, high, medium, or low, or to a threat type such as malware or intrusion attempt. This dramatically reduces analyst workload and speeds triage by prioritizing which alerts demand immediate human attention, directly solving the high-volume problem.

Why A is Wrong: Applying filters on specific alerts is a rule-based operation achievable without ML using simple log management tools. It requires no learning capability and does not adapt to new or evolving threats.

Why B is Wrong: Automatically patching systems is a remediation action requiring validated, controlled processes. Having an ML system autonomously patch production systems without human oversight poses unacceptable operational and security risk.

Why D is Wrong: Summarizing alert content is a useful generative AI function but does not provide prioritization value for triage. Classification tells analysts what to act on first; summarization only rephrases existing information.

Basic Concept: Threat modeling for any system, and especially for agentic AI systems with multiple interacting components, begins with understanding the system ' s architecture and where trust boundaries exist. Trust boundaries define where data and control flows cross between components with different trust levels, representing potential attack surfaces. CompTIA SecAI+ Study Guide aligns with STRIDE and MITRE ATLAS threat modeling methodologies.

Why B is Correct: Identifying trust boundaries between components is the foundational first step in threat modeling. Agentic systems often involve multiple components such as the orchestrator, tools, APIs, data sources, and external services with different trust levels. Understanding where these boundaries exist reveals where untrusted inputs cross into trusted components, enabling the architect to systematically identify threats at each boundary before proceeding to risk quantification and control application.

Why A is Wrong: Applying compensating controls based on exposure findings is the final step in threat modeling, occurring after threats have been identified and risks quantified. Controls cannot be appropriately designed without first understanding the system ' s trust boundaries and threat landscape.

Why C is Wrong: Calculating risk to resources based on data sensitivity is a risk assessment step that occurs after trust boundaries are mapped and potential threats are identified. Risk quantification requires knowing what threats exist at each boundary first.

Why D is Wrong: Scanning for OWASP Top 10 vulnerabilities is a technical vulnerability assessment activity. While valuable, it comes after the architectural analysis of trust boundaries and threat identification phases of threat modeling.

Basic Concept: A denial-of-wallet (DoW) attack deliberately generates excessive API calls or token consumption to exhaust an organization ' s AI budget. Since LLM providers charge based on tokens processed, attackers can cause significant financial damage by driving massive usage. CompTIA SecAI+ Study Guide addresses financial abuse vectors in AI systems.

Why E is Correct: API rate controls limit the number of requests a user or application can make within a defined time period. By capping request frequency, rate controls directly prevent attackers from generating the massive API call volume needed to execute a denial-of-wallet attack.

Why F is Correct: Output token controls cap the maximum number of tokens the model can generate per response. Since billing is based on tokens consumed including outputs, limiting output tokens directly caps the cost per request, preventing attackers from triggering extremely long, expensive responses.

Why A is Wrong: Endpoint access controls manage device or network access. They do not directly limit token consumption or API call volume that drives denial-of-wallet costs.

Why B is Wrong: A CDN distributes content geographically to improve performance and absorb traffic. It does not control LLM API billing or token consumption.

Why C is Wrong: Model fine-tuning adjusts model parameters for improved performance on specific tasks. It is a training process that does not address active cost-exhaustion attacks.

Why D is Wrong: Modality controls restrict which input types such as text, images, or audio a model accepts. While useful for reducing attack surface, they do not directly address the rate or volume of API calls in a DoW attack.