AIF-C01 Exam Dumps : AWS Certified AI Practitioner Exam

When a model is trained on a dataset containing confidential or sensitive data, the model may inadvertently learn patterns from this data, which could then be reflected in its inference responses. To ensure that a model does not generate responses based on confidential data, the most effective approach is to remove the confidential data from the training dataset and then retrain the model.

Explanation of Each Option:

Option A (Correct): " Delete the custom model. Remove the confidential data from the training dataset. Retrain the custom model. " This option is correct because it directly addresses the core issue: the model has been trained on confidential data. The only way to ensure that the model does not produce inferences based on this data is to remove the confidential information from the training dataset and then retrain the model from scratch. Simply deleting the model and retraining it ensures that no confidential data is learned or retained by the model. This approach follows the best practices recommended by AWS for handling sensitive data when using machine learning services like Amazon Bedrock.

Option B: " Mask the confidential data in the inference responses by using dynamic data masking. " This option is incorrect because dynamic data masking is typically used to mask or obfuscate sensitive data in a database. It does not address the core problem of the model beingtrained on confidential data. Masking data in inference responses does not prevent the model from using confidential data it learned during training.

Option C: " Encrypt the confidential data in the inference responses by using Amazon SageMaker. " This option is incorrect because encrypting the inference responses does not prevent the model from generating outputs based on confidential data. Encryption only secures the data at rest or in transit but does not affect the model ' s underlying knowledge or training process.

Option D: " Encrypt the confidential data in the custom model by using AWS Key Management Service (AWS KMS). " This option is incorrect as well because encrypting the data within the model does not prevent the model from generating responses based on the confidential data it learned during training. AWS KMS can encrypt data, but it does not modify the learning that the model has already performed.

AWS AI Practitioner References:

Data Handling Best Practices in AWS Machine Learning: AWS advises practitioners to carefully handle training data, especially when it involves sensitive or confidential information. This includes preprocessing steps like data anonymization or removal of sensitive data before using it to train machine learning models.

Amazon Bedrock and Model Training Security: Amazon Bedrock provides foundational models and customization capabilities, but any training involving sensitive data should follow best practices, such as removing or anonymizing confidential data to prevent unintended data leakage.

The correct answer is A – Create an AI agent. Amazon Bedrock Agents provide autonomous orchestration abilities that allow an AI system to interpret user queries, convert them into structured API calls, retrieve data, generate formatted outputs (like CSVs), and interact with external systems such as Amazon S3. According to AWS documentation, Bedrock Agents combine LLM reasoning with tool use, meaning they execute multi-step workflows such as querying OpenSearch, processing results, generating files, and uploading to storage—all without custom coding. The agent defines actions, APIs, and data transformation steps, making it ideal for automated enterprise workflows. Few-shot prompting (B) only influences text generation and cannot perform external actions like uploading to S3. A hand-coded software application (C) is possible but contradicts the goal of using AI for orchestration and requires more operational effort. A decision tree (D) cannot execute API workflows. Bedrock Agents are explicitly designed to perform multi-step tasks like this.

Referenced AWS Documentation:

Amazon Bedrock Agents – Tool Use and Workflow Automation

AWS Generative AI Best Practices – Agent-Based Architectures

AWS documentation defines prompt injection as a security and safety risk in which a user crafts input designed to override, manipulate, or bypass system-level instructions, safeguards, or intended model behavior . The example provided is a classic prompt injection attempt, where the user explicitly instructs the AI assistant to ignore prior rules and operate without restrictions.

In this scenario, the attacker is not exploiting training data or causing factual errors, but rather attempting to change the control flow and behavior of the AI system through malicious or manipulative prompts. AWS identifies prompt injection as a critical risk for generative AI systems, especially those exposed to end users through chat interfaces, APIs, or customer-facing applications.

The other options do not apply. Data bias relates to skewed or unfair training data. Hallucination refers to generating incorrect or fabricated information. Data exposure involves leaking sensitive or private data. None of these describe an attempt to override system instructions.

AWS recommends multiple mitigation strategies for prompt injection risks, including instruction hierarchy enforcement, prompt isolation, input validation, output filtering, and grounding responses using techniques such as Retrieval Augmented Generation . AWS also emphasizes the importance of clearly separating system instructions from user inputs to prevent unauthorized behavior changes.

Prompt injection is categorized by AWS as part of Responsible AI and security governance , highlighting the need for robust guardrails when deploying AI assistants in production. Therefore, the correct answer is prompt injection.