Free Practice Questions for CompTIA CY0-001 Exam

Basic Concept: Human-in-the-loop is a design pattern where AI systems generate recommendations or decisions but require human review and approval before those recommendations are acted upon. This approach maintains human oversight and accountability in AI-assisted workflows. CompTIA SecAI+ Study Guide covers human-in-the-loop as a key responsible AI principle and operational pattern.

Why C is Correct: The scenario precisely describes the human-in-the-loop pattern: the AI system identifies potential issues and provides recommendations, but an administrator must review those recommendations before any action is taken. This deliberate inclusion of human judgment in the AI ' s decision or recommendation workflow ensures human oversight is maintained, which is the defining characteristic of the human-in-the-loop process.

Why A is Wrong: Data validation verifies that data meets expected quality standards and formats before being used in AI processing. It is a data quality control activity, not a workflow pattern describing human review of AI recommendations.

Why B is Wrong: Data preparation involves transforming raw data into a format suitable for AI model training or inference. It encompasses cleaning, normalizing, and formatting data, not the process of human review of AI-generated recommendations during system updates.

Why D is Wrong: Model evaluation assesses a model ' s performance against metrics such as accuracy, precision, and recall on test datasets. It is a technical assessment of model quality, not a workflow process where humans review AI-generated recommendations before acting on them.

The described problem is hallucination: the LLM is generating plausible-looking information that is not grounded in real-world facts. Retrieval-augmented generation is the best option because RAG supplements the model ' s prompt with information retrieved from an authoritative external knowledge source before the response is generated. This allows incident- management responses to be grounded in actual tickets, security documentation, threat intelligence, asset information, or other trusted records instead of relying exclusively on the model ' s internal parameters. CompTIA SecAI+ explicitly includes RAG, vector storage, and embeddings within its AI data concepts and also identifies hallucinations as an issue that organizations must monitor and audit. Watermarking helps identify AI-generated content but does not improve factual grounding. Output filtering can block prohibited or unsafe output patterns, but it cannot reliably supply missing factual information. Data rebalancing addresses uneven distributions in training datasets and is unrelated to grounding an LLM ' s incident-management responses. RAG therefore most directly reduces unsupported or fabricated information by giving the model relevant factual context at inference time.

================

Basic Concept: System prompt injection — where an unauthorized party modifies the AI system ' s core instructions — represents a serious integrity attack. Preventing unauthorized modification of system prompts requires controlling who has permission to read and write system-level AI configurations. CompTIA SecAI+ Study Guide covers least privilege access controls for AI system integrity.

Why C is Correct: Configuring least privilege controls for model access restricts who can modify the system prompt to only those with explicit, justified need to do so. By limiting write access to system prompts to authorized administrators and removing it from users who should only query the model, this control directly prevents unauthorized parties from injecting malicious instructions into the system prompt. Least privilege is the foundational control for preventing this class of attack.

Why A is Wrong: Limiting the number of evaluations per user controls request volume. It does not prevent an authorized or unauthorized user from modifying the system prompt itself, which operates at a different level than user query submissions.

Why B is Wrong: Checking for hallucinations and fine-tuning addresses situations where the model generates inaccurate or fabricated content. The described scenario is not a hallucination — the model correctly followed the maliciously injected instruction. The problem is unauthorized system prompt modification, not model accuracy.

Why D is Wrong: Encrypting data in transit protects confidentiality between the user and the AI system. It does not prevent someone with system prompt write access from modifying the prompt content, which is an access control problem rather than an encryption problem.

OWASP is the best answer because it publishes the Top 10 for Large Language Model Applications, a resource specifically structured around significant security vulnerabilities and attack patterns affecting LLM-based applications. CompTIA SecAI+ Objective 2.1 directly lists the OWASP Top 10 and specifically the LLM Top 10 as an AI threat-modeling resource. MITRE ATLAS is also highly relevant to AI security, but its purpose is broader: it catalogs adversarial tactics, techniques, and procedures associated with attacks against AI and machine learning systems. The MIT AI Risk Repository aggregates a broad range of AI risks rather than functioning as the recognized LLM application vulnerability Top 10. NIST AI RMF provides a risk-management framework for governing and managing AI risks but is not primarily a vulnerability catalog for LLM applications. Since the question asks for the resource that most directly captures widely recognized threat vectors and common vulnerabilities associated specifically with LLM applications, OWASP ' s LLM-focused Top 10 is the most precise match.

Regulatory requirements are the most critical consideration because they can establish mandatory restrictions on how organizational, personal, regulated, or otherwise sensitive information may be processed by AI systems. CompTIA SecAI+ places private versus public models directly within the corporate-policy portion of AI governance, risk, and compliance and connects those decisions with sensitive data governance, third-party evaluations, and regulatory obligations. A public model may send data to infrastructure controlled by an external provider, potentially creating concerns involving data residency, retention, confidentiality, processing purposes, and cross-border transfers. A private model can provide greater organizational control over these factors. Model security remains essential, but a technically secure architecture can still be noncompliant if it violates applicable legal or regulatory obligations. Applicability determines whether a model is suitable for the intended use case but is not a governing compliance control. Responsible AI principles provide important guidance around fairness, safety, transparency, privacy, and accountability, but binding regulatory obligations generally take precedence when determining permissible deployment conditions. Therefore, regulations are the controlling consideration when deciding whether public or private AI models are acceptable for sensitive training workloads.

================

Basic Concept: AI systems can inadvertently reveal sensitive information such as PII, credentials, or internal data in their outputs when not properly controlled. Sensitive information disclosure is a critical OWASP LLM Top 10 risk. CompTIA SecAI+ Study Guide covers both vulnerability identification and appropriate data protection controls for AI outputs.

Why D is Correct: The scenario describes the AI system outputting sensitive information in its responses, which is a sensitive information disclosure vulnerability. The appropriate control is masking, which replaces sensitive data values such as credit card numbers, SSNs, or API keys with redacted or tokenized equivalents in the model ' s outputs before they are returned to users. This prevents the AI from disclosing sensitive data while still providing useful responses.

Why A is Wrong: Prompt injection involves crafting inputs to override model instructions. If the penetration test revealed sensitive information, the primary vulnerability is the disclosure of that sensitive data, not the injection mechanism itself. EDR monitors endpoint behavior, not AI output content.

Why B is Wrong: Model hallucinations produce fabricated information rather than disclosing real sensitive data. The described scenario involves actual sensitive information being revealed, not fictitious content generation.

Why C is Wrong: Jailbreaking circumvents safety restrictions but the primary harm demonstrated is sensitive data exposure. RBAC manages access permissions but does not prevent the model from including sensitive data in responses once access is granted.

Why E is Wrong: Role impersonation involves the AI pretending to be a different entity. This may be a secondary technique used by the penetration tester but the primary vulnerability described is the disclosure of actual sensitive information in the output.

Basic Concept: Successful AI adoption at an organizational level requires a centralized governance body that standardizes AI practices, promotes best practices, and ensures consistent, safe, and effective AI deployment across the organization. CompTIA SecAI+ Study Guide covers AI organizational governance structures under Domain 4.

Why A is Correct: An AI Center of Excellence (CoE) is an organizational unit specifically designed to govern, standardize, and advance AI adoption. It develops and publishes policies, creates approved patterns for AI usage, evaluates new AI use cases, provides expert guidance, and maintains governance oversight. The CoE exactly matches the described need for a structure to evaluate, publish, and approve AI usage patterns across the organization.

Why B is Wrong: An AI legal affairs office focuses on legal compliance, intellectual property, and regulatory matters related to AI. While important for legal risk management, it does not fulfill the broader governance mandate of establishing and approving AI usage patterns and best practices across the organization.

Why C is Wrong: An AI audit department conducts post-implementation reviews and compliance assessments of existing AI systems. It is a retrospective and oversight function rather than a proactive body for developing and approving AI usage patterns and policies.

Why D is Wrong: An AI data science division is a technical team focused on building AI models and solutions. It is a development function rather than a governance structure designed to create policies, evaluate AI patterns, and provide cross-organizational oversight of AI adoption.

The data scientist is the most appropriate role because correcting biased source data requires examining the datasets used to develop, train, validate, or refine the model and then modifying the data preparation or model-development process. Data scientists work directly with training data, feature selection, statistical distributions, model development, and evaluation, which places them in the strongest position to identify biased inputs and retrain or adjust the model using more representative information. CompTIA SecAI+ includes the data scientist as a formal AI governance role and separately identifies fairness, introduction of bias, accuracy, and model performance as key responsible-AI risks. A platform engineer primarily manages the infrastructure supporting AI workloads. A cybersecurity analyst focuses on security threats, monitoring, and defensive controls rather than correcting discriminatory training data. An AI architect designs the broader architecture and integration of AI solutions but normally does not perform the detailed dataset preparation and model-training work required here. Because the problem originates in biased data sources, the data scientist is the role closest to the underlying cause.

================

Basic Concept: A chatbot that learns from user prompts is vulnerable to data poisoning through conversational injection. Malicious users can deliberately introduce false information that the chatbot incorporates into its knowledge, corrupting responses for subsequent users. CompTIA SecAI+ Study Guide identifies this as a real-time data poisoning vector requiring guardrail controls.

Why D is Correct: Guardrails prevent the chatbot from accepting and incorporating unverified, irrelevant, or potentially malicious information injected by users. They enforce boundaries on what the chatbot can learn from user interactions, validate that information aligns with the system ' s purpose and known facts, and block outputs based on poisoned knowledge. Guardrails are specifically designed to prevent the type of conversational data poisoning demonstrated where a user ' s false claim corrupted the model ' s subsequent responses.

Why A is Wrong: Data encryption protects the confidentiality of data in transit and at rest. It does not prevent a chatbot from accepting and acting on false information that users deliberately inject into the conversation.

Why B is Wrong: API rate limiting restricts the frequency of requests. While it can limit the number of poisoning attempts a single user can make, it does not prevent the chatbot from learning from and propagating false information when requests are made at an acceptable rate.

Why C is Wrong: Transfer learning is a training technique that adapts knowledge from one domain to another. It is a model development approach, not a runtime control that prevents users from injecting false information into a deployed chatbot.