Security, Compliance and Governance for AI

Question 1

What is a defense in depth security strategy?

Answer 1

Uses multiple redundant defenses to protect your AWS accounts, workloads, data, and assets.

Question 2

How do you protect data at rest?

Answer 2

Encrypt with AWS Key Management Service (AWS KMS)

Question 3

How do you protect data in transit?

Answer 3

1) AWS Certificate Manager (ACM) 2)AWS Private Certificate Authority (AWS Private CA).

Question 4

Amazon service for identity and access management

Answer 4

AWS Identity and Access Management (IAM).

Question 5

AWS application protection services

Answer 5

measures to protect against various threats, such as unauthorized access, data breaches, denial-of-service (DoS) attacks, and other security vulnerabilities.
AWS Shield
Amazon Cognito

Question 6

Infrastructure protection services

Answer 6

AWS Identity and Access Management (IAM)
IAM user groups and network access control lists (network ACLs)

Question 7

AWS services that provide network and edge protection

Answer 7

Amazon Virtual Private Cloud (Amazon VPC)
AWS WAF

Question 8

Threat detection and incident response services

Answer 8

AWS Security Hub
Amazon GuardDuty

Question 10

What is Data logging?

Answer 10

Data logging involves the systematic recording of data related to the processing of an AI workload. This can include the following:

Tracking inputs
Tracking outputs
Model performance metrics
System events

Question 11

What are prompt injections?

Answer 11

In these attacks, adversaries attempt to manipulate the input prompts of generative AI models to generate malicious or undesirable content

Question 12

The Open Web Application Security Project (OWASP)

Answer 12

Industry standard list of the top 10 vulnerabilities that can impact a generative AI LLM system

Question 13

The Open Web Application Security Project (OWASP) Top 10

Answer 13

Prompt injection: Malicious user inputs that can manipulate the behavior of a language model
2

Insecure output handling: Failure to properly sanitize or validate model outputs, leading to security vulnerabilities
3

Training data poisoning: Introducing malicious data into a model’s training set, causing it to learn harmful behaviors
4

Model denial of service: Techniques that exploit vulnerabilities in a model’s architecture to disrupt its availability
5

Supply chain vulnerabilities: Weaknesses in the software, hardware, or services used to build or deploy a model
6

Sensitive information disclosure: Leakage of sensitive data through model outputs or other unintended channels
7

Insecure plugin design: Flaws in the design or implementation of optional model components that can be exploited
8

Excessive agency: Granting a model too much autonomy or capability, leading to unintended and potentially harmful actions
9

Overreliance: Over-dependence on a model’s capabilities, leading to over-trust and failure to properly audit its outputs
10

Model theft: Unauthorized access or copying of a model’s parameters or architecture, allowing for its reuse or misuse

Question 14

What does AWS Security Hub provide?

Answer 14

a single dashboard to view all security findings, and to create and run automated playbooks.

Question 15

What does AWS Key management service (KMS) do?

Answer 15

AWS KMS encrypts data and gives customers the choice and control of using AWS managed keys or customer-managed keys to protect their data.

Question 16

What is Amazon GuardDuty?

Answer 16

A threat detection service that monitors for suspicious activity and unauthorized behavior to protect AWS accounts, workloads, and data

Question 17

What is AWS Shield Advanced?

Answer 17

protect workloads against Distributed Denial of Service (DDoS) events. AWS Shield Advanced includes AWS WAF and AWS Firewall Manager.

Question 18

What is cataloging?

Answer 18

the systematic organization and documentation of the datasets, models, and other resources used in the development of a generative AI system.

Question 18

What is Amazon Inspector?

Answer 18

an automated vulnerability management service that continually scans AWS workloads for software vulnerabilities and unintended network exposure.

Question 18

What is Amazon Detective?

Answer 18

streamlines the investigative process and helps security teams conduct faster and more effective forensic investigations.

Question 18

What are model cards?

Answer 18

standardized format for documenting the key details about an ML model, including its intended use, performance characteristics, and potential limitations.

In the context of generative AI, model cards can be used to provide source citations and data origin documentation

Question 18

Data lineage

Answer 18

Technique used to track history of data. data lineage can be used to document the journey of the training data, from its initial sources to the final model.

Question 18

Prompt Injection

Answer 18

Influencing the outputs by embedding specific instructions within the prompts themselves

Question 18

Exposure

Answer 18

The risk of exposing sensitive or confidential information to a model during training or inference. The model can then reveal this sensitive data from their training corpus, leading to potential data leaks or privacy violations.

Question 19

5 types of machine learning

Answer 19

1) Supervised
2) Unsupervised
3) Semi-Supervised (small amount of labeled data and large amount of unlabeled data)
4) Reinforcement Learning
5) Deep Learning

Question 20

What is AWS Artifact?

Answer 20

designed to provide access to a wide range of AWS compliance reports, including those from Independent Software Vendors (ISVs). AWS Artifact allows users to configure settings to receive notifications when new compliance documents or reports are available