CY0-001 — CompTIA SecAI+ (CY0-001) Exam Blueprint

Practical CY0-001 AI security exam blueprint for CompTIA SecAI+ final review.

How to Use This Exam Blueprint

Use this checklist as a practical readiness map for the CompTIA SecAI+ (CY0-001) exam. It is organized around the kinds of AI security knowledge, decisions, controls, and troubleshooting judgment a candidate should be able to apply.

Because exact official weighting is not provided here, the sections below are presented as readiness areas, not as guaranteed exam percentages. For best results:

  1. Review each topic area.
  2. Mark items you can explain and apply without notes.
  3. For weak areas, practice with short scenarios: identify the risk, choose a control, justify the tradeoff.
  4. In the final week, focus on missed decision points, vocabulary gaps, and scenario speed.

Topic-area readiness table

Readiness areaWhat to knowWhat “ready” looks like
AI, ML, and generative AI fundamentalsModel types, training vs. inference, supervised/unsupervised learning, embeddings, tokens, prompts, agents, RAG, model evaluationYou can explain how an AI system works at a security-relevant level without turning every question into generic cybersecurity
AI risk and governanceRisk assessment, policy, ownership, acceptable use, data classification, auditability, third-party risk, human oversightYou can map an AI use case to risk controls and governance artifacts
Secure AI system architectureData pipelines, model endpoints, APIs, identity, network segmentation, secrets, storage, logging, deployment boundariesYou can identify where controls belong in an AI workflow
Data security and privacySensitive data handling, consent, minimization, masking, tokenization, anonymization, encryption, retention, data lineageYou can recognize privacy leakage and choose practical data protection controls
Adversarial AI threatsPrompt injection, poisoning, evasion, model extraction, model inversion, membership inference, jailbreaking, hallucination abuseYou can match attack patterns to mitigations
Generative AI and LLM securitySystem prompts, prompt hierarchy, plugins/tools, agents, RAG, embeddings, vector stores, output handlingYou can secure an LLM application beyond “filter the prompt”
MLOps and LLMOps securityModel registry, CI/CD, pipeline integrity, model versioning, reproducibility, evaluation gates, rollback, drift monitoringYou can secure the lifecycle from development through production monitoring
Application and API security for AIAuthentication, authorization, rate limiting, input validation, output encoding, API gateway controls, abuse preventionYou can apply normal AppSec controls to AI-specific data flows
Cloud, infrastructure, and endpoint controlsIAM, compute isolation, storage permissions, network access, key management, container security, workload monitoringYou can select infrastructure controls that reduce AI workload risk
Security monitoring and incident responseAI logs, prompt logs, model behavior telemetry, anomaly detection, alert triage, containment, evidence preservationYou can respond to AI incidents without destroying forensic value
Testing and validationRed teaming, prompt testing, bias/fairness checks, security evaluations, regression testing, adversarial testingYou can design tests that reveal misuse, leakage, unsafe behavior, or degraded performance
Compliance and ethicsPrivacy, explainability, accountability, fairness, transparency, safety, documentation, audit trailsYou can distinguish compliance, ethics, and security concerns in scenarios

AI and machine learning fundamentals checklist

Core concepts to review

  • Explain the difference between training, validation, testing, and inference.
  • Distinguish model, algorithm, dataset, feature, label, embedding, token, and parameter.
  • Recognize when a system uses:
    • Supervised learning
    • Unsupervised learning
    • Reinforcement learning
    • Deep learning
    • Generative AI
    • Retrieval-augmented generation
    • Agentic workflows
  • Explain why AI systems can fail differently from deterministic software.
  • Identify where randomness, probability, confidence scores, thresholds, and model uncertainty affect security decisions.
  • Describe the difference between model behavior and application behavior.
  • Recognize the security impact of:
    • Overfitting
    • Underfitting
    • Drift
    • Hallucination
    • Bias
    • Data leakage
    • Model degradation

Can you do this?

PromptReady if you can…
A model performs well in testing but poorly in production.Identify possible causes such as drift, data mismatch, overfitting, changed inputs, or pipeline defects.
A chatbot gives confident but false answers.Explain hallucination risk and controls such as grounding, retrieval constraints, citations, validation, and human review.
A model makes security decisions using a threshold.Explain the tradeoff between false positives and false negatives.
A team wants to train a model on all available business data.Identify data classification, privacy, consent, minimization, and retention concerns.

AI security governance and risk management

Governance artifacts to recognize

ArtifactPurposeExam-readiness cue
AI acceptable use policyDefines approved and prohibited AI usageKnow how it reduces shadow AI and unsafe data entry
Data classification policyLabels data by sensitivityKnow how it drives access, encryption, masking, and retention
AI risk assessmentIdentifies threats, impact, likelihood, and controlsKnow how to prioritize mitigation
Model card or system cardDocuments intended use, limitations, training data notes, evaluation resultsKnow how documentation supports transparency and review
Data lineage recordTracks source, transformation, and use of dataKnow why it matters for audits and incident response
Third-party AI assessmentEvaluates vendor, model, API, data usage, and contractual riskKnow what questions to ask before sending data externally
Human-in-the-loop procedureDefines when humans approve, override, or review AI outputKnow where automation needs oversight
Incident response playbookDefines detection, triage, containment, recovery, and lessons learnedKnow what changes for AI-specific incidents

Risk decision checklist

  • Identify the AI asset: model, dataset, prompt, vector index, endpoint, pipeline, plugin, agent, or output.
  • Identify the threat actor: external attacker, insider, malicious user, compromised vendor, careless employee, or automated bot.
  • Identify the harm:
    • Data exposure
    • Unsafe output
    • Fraud or abuse
    • Model theft
    • Service disruption
    • Compliance violation
    • Reputational damage
  • Select controls that match the risk, not just generic controls.
  • Decide whether risk should be reduced, transferred, accepted, or avoided.
  • Document ownership and accountability for the AI system.
  • Confirm monitoring and review frequency.
  • Consider whether human review is required before action is taken.

Common governance traps

TrapWhy it matters
Treating AI as only a software problemAI risk includes data, model behavior, governance, and misuse.
Trusting vendor claims without reviewThird-party AI tools can introduce data handling, retention, and visibility issues.
Failing to document intended useModels often become risky when reused outside their original context.
No owner for model outputSomeone must be accountable for decisions, escalations, and exceptions.
Logging everything without classificationPrompt and response logs may contain sensitive data.

Data security, privacy, and AI pipelines

Data lifecycle checklist

StageWhat to reviewSecurity questions
CollectionSources, consent, sensitivity, legality, qualityIs the data appropriate and authorized for this use?
IngestionTransfer, validation, malware scanning, schema checksCan untrusted data poison or break the pipeline?
StorageEncryption, access control, segmentation, retentionWho can read, modify, export, or delete it?
PreparationCleaning, labeling, feature engineering, maskingCould sensitive values leak into features or labels?
Training or fine-tuningDataset selection, isolation, reproducibilityCan training data be traced, reviewed, and protected?
RetrievalEmbeddings, vector stores, indexes, document chunksCan users retrieve data they should not see?
InferenceInput handling, output filtering, access decisionsDoes the system reveal sensitive information?
LoggingPrompt logs, response logs, telemetry, audit trailsAre logs protected and minimized?
Archival or deletionRetention, legal hold, secure deletionCan data be removed when required?

Data protection controls

  • Data classification
  • Data minimization
  • Access control and least privilege
  • Encryption in transit
  • Encryption at rest
  • Key management
  • Tokenization
  • Masking or redaction
  • Anonymization or pseudonymization
  • Data loss prevention
  • Retention controls
  • Secure deletion
  • Audit logging
  • Data lineage tracking

Can you do this?

ScenarioBest readiness response
Employees paste customer records into a public AI tool.Identify data exposure, policy violation, possible privacy issue, and need for approved tooling, DLP, training, and access controls.
A RAG system returns HR documents to non-HR users.Check document-level authorization, index construction, metadata filters, identity propagation, and retrieval controls.
A data scientist wants production data for testing.Recommend masking, synthetic data, controlled access, approved environments, and data minimization.
A model was trained on data that should have been deleted.Consider lineage, retraining, legal review, incident handling, and retention process gaps.

Adversarial AI threat checklist

Threats to recognize

ThreatWhat it targetsWhat it looks likeCommon mitigations
Prompt injectionLLM instructions and contextUser input tells model to ignore instructions or reveal hidden dataInput handling, prompt isolation, tool permissions, output validation, least privilege
JailbreakingSafety and policy controlsAttempts to bypass guardrails through roleplay, encoding, or instruction tricksGuardrails, policy enforcement, model evaluation, monitoring, defense in depth
Data poisoningTraining or fine-tuning dataMalicious samples degrade or manipulate model behaviorData validation, source trust, anomaly detection, lineage, review workflows
Evasion attackModel inferenceInput is modified to avoid detection or change classificationRobust testing, adversarial evaluation, monitoring, layered controls
Model extractionModel confidentialityRepeated queries used to approximate or steal model behaviorRate limiting, monitoring, watermarking where applicable, access control
Model inversionTraining data privacyAttacker infers sensitive information from model outputsOutput limits, privacy-preserving training, access control, monitoring
Membership inferenceDataset privacyAttacker determines whether a record was in training dataRegularization, privacy controls, output restriction, evaluation
Training data leakageData confidentialityModel reveals memorized secrets or sensitive textData cleansing, secret scanning, output filtering, retraining if needed
Supply chain compromiseDependencies and modelsMalicious library, model artifact, or container imageSigned artifacts, SBOM, scanning, trusted registries, CI/CD controls
Tool abuseAI agents and pluginsModel calls tools in unsafe waysTool permission scoping, approval gates, sandboxing, action validation

Attack-to-control matching

If you see…Think first about…
“Ignore previous instructions”Prompt injection
Model returns hidden system instructionsPrompt leakage or prompt injection weakness
Model accesses documents outside user permissionsBroken authorization in RAG or retrieval layer
Repeated high-volume queries against model endpointExtraction, scraping, denial of service, or abuse
Performance suddenly changes after new training dataPoisoning, drift, pipeline issue, or data quality problem
Agent sends email, transfers data, or modifies records without approvalExcessive tool permissions and missing human approval
Sensitive data appears in completionsData leakage, memorization, poor filtering, or unsafe retrieval

Generative AI, LLM, RAG, and agent security

LLM application components

ComponentSecurity focus
System promptProtect from disclosure, avoid relying on it as the only control
User promptTreat as untrusted input
Context windowLimit sensitive content and prevent cross-user contamination
Retrieval layerEnforce authorization before retrieval and before response generation
Vector databaseProtect embeddings, metadata, source documents, and indexes
Tools and pluginsRestrict actions, permissions, network access, and data access
Output handlerValidate, filter, encode, and log safely
Feedback loopPrevent malicious feedback from poisoning future behavior
MonitoringCapture abuse patterns, unsafe outputs, latency, cost anomalies, and policy violations

RAG readiness checklist

  • Explain how retrieval-augmented generation differs from training or fine-tuning.
  • Identify where sensitive data can leak:
    • Source documents
    • Chunks
    • Embeddings
    • Metadata
    • Retrieved context
    • Prompt logs
    • Final responses
  • Enforce authorization at retrieval time.
  • Preserve source document permissions in the index.
  • Validate that users cannot retrieve documents by prompt manipulation.
  • Review chunking strategy for overexposure of unrelated content.
  • Protect vector indexes with access control and encryption.
  • Monitor retrieval anomalies.
  • Test for cross-tenant and cross-user leakage.
  • Avoid assuming embeddings are automatically non-sensitive.

Agent security checklist

  • List every tool the agent can call.
  • Assign least privilege to each tool.
  • Separate read-only tools from write/action tools.
  • Require approval for high-impact actions.
  • Validate tool inputs and outputs.
  • Limit network destinations.
  • Use sandboxing where possible.
  • Log tool calls and decisions.
  • Prevent prompt content from directly becoming privileged commands.
  • Create rollback or recovery procedures for agent-initiated changes.

Decision path: securing an AI feature

    flowchart TD
	    A[New AI feature request] --> B{Does it process sensitive data?}
	    B -- Yes --> C[Classify data and apply privacy controls]
	    B -- No --> D[Define intended use and misuse cases]
	    C --> D
	    D --> E{Can it take actions or call tools?}
	    E -- Yes --> F[Apply least privilege, approval gates, and tool logging]
	    E -- No --> G[Secure prompts, retrieval, and outputs]
	    F --> H[Test for abuse, leakage, and unsafe behavior]
	    G --> H
	    H --> I{Risk acceptable?}
	    I -- No --> J[Add controls or redesign]
	    I -- Yes --> K[Deploy with monitoring and review]

Secure AI architecture and design

Architecture control checklist

LayerControls to review
IdentitySSO, MFA, least privilege, service accounts, workload identity, separation of duties
NetworkSegmentation, private connectivity where appropriate, firewall rules, egress control, API gateways
ComputeHardened images, container isolation, patching, runtime monitoring, resource limits
StorageEncryption, access policies, backup, retention, versioning, object permissions
Model endpointAuthentication, authorization, throttling, abuse detection, input/output controls
SecretsSecret vaults, rotation, no secrets in prompts, code, images, or logs
CI/CDApproved repositories, code review, artifact signing, scanning, promotion gates
ObservabilityLogs, metrics, traces, model behavior telemetry, alerting, audit trails
ResilienceRollback, fail-safe behavior, fallback paths, degraded-mode planning
GovernanceApproval records, risk assessments, documentation, periodic review

Secure design questions

  • What data does the AI system need, and what data should it never see?
  • Who can submit prompts, files, queries, or API requests?
  • Who can view outputs?
  • What identities are used by the application, model endpoint, retrieval service, and tools?
  • Are permissions based on the user, the service, or both?
  • Can the AI system call external services?
  • Can the AI system perform write actions?
  • What happens if the model produces unsafe, false, or unauthorized output?
  • What is logged, and who can access those logs?
  • How is model or prompt configuration changed and approved?
  • How is rollback performed?

Application security and API controls for AI systems

AppSec controls that still matter

ControlAI-specific exam cue
AuthenticationConfirm user, service, and workload identity before AI access
AuthorizationEnforce permissions before data retrieval and tool use
Input validationTreat prompts, documents, URLs, files, and metadata as untrusted
Output validationCheck generated text, code, commands, links, and structured output
Rate limitingReduce abuse, scraping, model extraction, and cost spikes
API gatewayCentralize auth, throttling, logging, and routing
Secure session managementPrevent cross-user context leakage
Error handlingAvoid exposing prompts, stack traces, model details, or secrets
Secure codingPrevent injection, deserialization, path traversal, SSRF, and dependency risks
Content safety controlsDetect toxic, unsafe, confidential, or policy-violating output

AI API scenario checks

ScenarioWhat to check
Public chatbot endpoint receives high-volume requestsRate limiting, bot controls, abuse monitoring, cost alerts, endpoint authentication if required
LLM summarizes uploaded filesMalware scanning, file type validation, size limits, data classification, retention policy
Model generates codeSecure code review, dependency scanning, sandboxed execution, warning labels
AI service returns structured JSON used by an applicationSchema validation, safe parsing, allowlists, error handling
User prompt includes a URLSSRF protections, URL validation, network egress controls, safe fetch service

MLOps, LLMOps, and secure lifecycle readiness

Lifecycle checklist

PhaseReadiness checks
DesignThreat model, data classification, intended use, abuse cases, control requirements
Data preparationSource validation, lineage, cleaning, labeling quality, secret scanning
DevelopmentSecure notebooks, repository controls, dependency review, peer review
Training/fine-tuningIsolated environment, approved data, tracked configuration, reproducible runs
EvaluationSecurity tests, quality metrics, bias checks, robustness tests, regression testing
PackagingSigned artifacts, model registry, versioning, metadata, SBOM where applicable
DeploymentApproval gates, environment separation, endpoint hardening, rollback plan
MonitoringDrift, abuse, leakage, latency, failures, unusual usage, cost anomalies
Change managementApproved updates, documented changes, comparison to baseline
RetirementDisable endpoints, revoke keys, archive or delete data, preserve required records

Model registry and artifact checks

  • Can you identify the approved model version?
  • Can you trace the model to its training data and configuration?
  • Are models stored in a trusted registry?
  • Are artifacts protected from unauthorized modification?
  • Are promotion steps documented?
  • Are rollback options available?
  • Are deprecated models disabled or restricted?
  • Are third-party models assessed before use?

Supply chain weak points

Weak pointRiskControl
Open-source modelHidden behavior, license issue, unsafe training dataVet source, scan artifacts, test behavior, document approval
Python/package dependencyMalicious or vulnerable libraryDependency scanning, pinned versions, trusted repositories
Container imageVulnerable runtime or embedded secretsImage scanning, minimal base images, secret scanning
Notebook environmentUntracked code, exposed credentialsAccess control, versioning, secrets management
CI/CD pipelineUnauthorized model or code promotionBranch protections, approval gates, signed artifacts
Dataset sourcePoisoned or unauthorized dataSource validation, lineage, sampling, anomaly detection

Security monitoring, detection, and incident response

What to monitor in AI systems

SignalWhy it matters
Authentication failuresCredential attacks or unauthorized access attempts
Unusual prompt patternsPrompt injection, jailbreak attempts, probing
High query volumeAbuse, extraction, denial of service, cost attack
Unusual retrieval patternsData scraping or authorization bypass
Sensitive output eventsData leakage or policy failure
Tool invocation logsAgent misuse or excessive permissions
Model performance driftData changes, degradation, or attack
Error rates and latencyAvailability and reliability issues
Cost anomaliesAbuse, runaway agents, inefficient prompts
Configuration changesUnauthorized prompt, model, or policy changes

AI incident response checklist

  • Classify the incident type:
    • Data exposure
    • Prompt injection
    • Unsafe output
    • Unauthorized tool action
    • Model or data poisoning
    • Model theft
    • Availability or cost attack
  • Preserve relevant evidence:
    • Prompts
    • Responses
    • Retrieval context
    • Tool calls
    • Model version
    • User identity
    • API logs
    • Dataset or pipeline changes
  • Contain the issue:
    • Disable affected endpoint
    • Revoke keys or tokens
    • Roll back model or prompt version
    • Disable tool access
    • Block abusive accounts or sources
  • Assess data impact.
  • Determine whether outputs influenced business decisions.
  • Notify appropriate internal stakeholders.
  • Remediate root cause.
  • Add detection or test cases to prevent recurrence.
  • Document lessons learned.

Triage decision cues

SymptomLikely investigation path
Model suddenly recommends unsafe actionsCheck prompt/config changes, model version, retrieval data, safety filters
Users see another department’s documentsCheck authorization propagation, vector metadata, index permissions
Endpoint costs spike overnightCheck query volume, agent loops, abuse, rate limits, token usage
Model classification accuracy dropsCheck drift, new data, poisoning, threshold changes, pipeline defects
Sensitive information appears in logsCheck logging policy, redaction, retention, access permissions

AI testing, validation, and evaluation

Testing types to know

Test typePurpose
Functional testingConfirms the AI feature works as intended
Security testingFinds exploitable weaknesses in inputs, outputs, APIs, permissions, and infrastructure
Adversarial testingTests evasion, prompt injection, poisoning, and misuse
Red teamingSimulates realistic attacker or malicious user behavior
Regression testingConfirms new changes do not reintroduce prior failures
Bias/fairness testingIdentifies disparate or inappropriate outcomes
Privacy testingDetects leakage, memorization, or exposure of sensitive data
Robustness testingMeasures behavior under malformed, unexpected, or hostile input
Performance testingReviews latency, availability, scalability, and resource use

Metrics and confusion matrix readiness

For classification scenarios, be comfortable with true positives, false positives, true negatives, and false negatives.

\[ \text{Accuracy} = \frac{TP + TN}{TP + TN + FP + FN} \]\[ \text{Precision} = \frac{TP}{TP + FP} \]\[ \text{Recall} = \frac{TP}{TP + FN} \]\[ \text{F1 Score} = 2 \times \frac{\text{Precision} \times \text{Recall}}{\text{Precision} + \text{Recall}} \]

Metric decision checks

If the scenario emphasizes…Think about…
Avoiding missed malicious eventsRecall / reducing false negatives
Avoiding unnecessary alerts or blocksPrecision / reducing false positives
Overall correct predictions in balanced dataAccuracy
Imbalanced datasetsPrecision, recall, F1, and confusion matrix over simple accuracy
Threshold tuningTradeoff between false positives and false negatives
Production performance changeDrift, data quality, pipeline change, or adversarial behavior

Privacy, compliance, and ethical AI readiness

Exam blueprint

  • Explain why privacy is not the same as security.
  • Identify sensitive, regulated, confidential, and proprietary data.
  • Apply data minimization to AI use cases.
  • Explain consent and purpose limitation at a high level.
  • Recognize when explainability or transparency is needed.
  • Identify bias and fairness concerns.
  • Recognize accountability gaps in automated decision-making.
  • Know why audit trails matter for AI decisions.
  • Understand human review and escalation for high-impact outputs.
  • Identify third-party data handling concerns.
  • Recognize retention and deletion issues in training data, logs, and indexes.

Ethics and governance scenario cues

Scenario wordingLikely concern
“The model cannot explain why it denied the request.”Explainability, accountability, auditability
“The training data underrepresents a population.”Bias, fairness, model performance gap
“Users are unaware their data is used for training.”Consent, transparency, purpose limitation
“The AI system makes final decisions without review.”Human oversight and accountability
“Logs contain prompts with personal information.”Privacy, minimization, log protection

Cloud, infrastructure, and operations checks

Infrastructure topics to review

TopicWhat to be ready for
IAMLeast privilege, role separation, service identities, key rotation, access review
Network securitySegmentation, ingress/egress control, private endpoints where appropriate, firewalling
Storage securityEncryption, bucket/container permissions, lifecycle policies, backup
Compute securityPatch management, hardened images, container security, workload isolation
Secrets managementVaulting, rotation, no hardcoded credentials, no secrets in prompts/logs
Key managementOwnership, access control, rotation, separation from data access
Logging and monitoringCentralized logs, alerting, retention, access control, tamper resistance
Cost and abuse controlsRate limits, quotas, alerts, anomaly detection, runaway job prevention
ResilienceBackups, rollback, failover, degraded mode, dependency planning
Environment separationDevelopment, test, staging, production isolation

Operational readiness questions

  • Can a compromised model endpoint access sensitive storage?
  • Can a compromised notebook access production data?
  • Are training jobs isolated from production workloads?
  • Are service accounts overprivileged?
  • Are model artifacts protected from tampering?
  • Are prompt templates and configuration files change-controlled?
  • Can logs be modified by the same identities being monitored?
  • Are emergency shutdown and rollback procedures defined?

Scenario and decision-point practice

Choose the best control

ScenarioBest first control direction
A chatbot must answer questions from internal documents but only according to user permissions.Identity-aware retrieval with document-level authorization and metadata filtering
A model endpoint is being queried thousands of times by one client.Rate limiting, abuse detection, authentication review, and monitoring
A team wants the AI agent to approve refunds automatically.Human approval gates, transaction limits, audit logs, and least-privilege tool access
Generated code is being copied directly into production.Secure code review, testing, dependency scanning, and developer training
An LLM plugin can access internal ticketing and email.Scope plugin permissions, validate actions, require approval for sensitive operations
Model performance drops after a dataset update.Investigate data quality, drift, poisoning, and pipeline changes
Customer data appears in generated responses.Contain, investigate retrieval/training/log sources, assess exposure, remediate leakage
A public model is downloaded for internal use.Assess provenance, license, security, behavior, and artifact integrity before approval

Identify the likely weakness

ClueLikely weakness
“The model was connected directly to production admin APIs.”Excessive privilege and missing approval gates
“The prompt says not to reveal secrets.”Overreliance on prompt instructions as a security boundary
“Everyone can query the same vector index.”Broken access control in retrieval
“Training data was copied from many locations with no records.”Missing data lineage and governance
“The model was updated outside the deployment pipeline.”Change management and supply chain weakness
“Developers use personal AI accounts for debugging.”Shadow AI and data exposure risk
“The system logs full prompts indefinitely.”Privacy, retention, and log access risk

Common weak areas and traps for CY0-001 preparation

Weak areaHow to fix it
Memorizing AI terms without security contextFor every term, ask: what can go wrong, and what control reduces the risk?
Treating LLM prompts as trusted instructionsRemember that user-controlled text is input, not policy enforcement.
Forgetting retrieval authorizationRAG security often fails because indexed data is not filtered by user permissions.
Confusing fine-tuning with RAGFine-tuning changes model behavior; RAG supplies external context at inference time.
Ignoring logs as sensitive dataPrompts, responses, and retrieval context can contain confidential information.
Overlooking agent tool permissionsThe model may be probabilistic, but tool actions can be real and high impact.
Choosing only one controlAI systems usually need layered controls across data, model, app, and infrastructure.
Assuming vendor AI tools remove customer responsibilityYou still need data governance, access control, monitoring, and usage policy.
Using accuracy for every evaluation questionConsider precision, recall, false positives, false negatives, and class imbalance.
Forgetting incident evidenceModel version, prompts, retrieved context, and tool calls may be critical evidence.

Final-week checklist

Seven-day review plan

TimeframeFocus
7 days outRevisit AI fundamentals, lifecycle, governance, and threat vocabulary
6 days outDrill adversarial AI attacks and match each to mitigations
5 days outReview RAG, vector store, prompt injection, and agent scenarios
4 days outPractice data privacy, lineage, logging, and third-party AI risk questions
3 days outReview MLOps/LLMOps, model registry, CI/CD, and supply chain controls
2 days outPractice mixed scenarios and explain why wrong answers are weaker
1 day outLight review: formulas, terms, traps, and decision cues; avoid cramming new material

Final readiness checks

  • I can explain the AI lifecycle from data collection to retirement.
  • I can identify AI-specific threats from short scenario clues.
  • I can match prompt injection, poisoning, evasion, extraction, inversion, and leakage to controls.
  • I can secure a RAG system using identity-aware retrieval and data controls.
  • I can explain why prompts are not reliable security boundaries.
  • I can identify sensitive data exposure in prompts, logs, embeddings, and outputs.
  • I can apply least privilege to AI tools, plugins, agents, and service accounts.
  • I can choose monitoring signals for AI misuse, drift, leakage, and abuse.
  • I can describe AI incident response evidence and containment steps.
  • I can apply precision, recall, false positives, and false negatives in simple scenarios.
  • I can distinguish governance, ethics, privacy, and technical security issues.
  • I can explain tradeoffs instead of selecting controls by keyword alone.

Practical next step

After you complete this checklist, move into timed scenario practice for CompTIA SecAI+ (CY0-001). Focus especially on questions that require choosing the best control for an AI system, identifying the likely attack from limited evidence, and explaining why a technically correct control may not be the best first action.

Browse Certification Practice Tests by Exam Family