Security, Compliance and Governance for AI Flashcards
What is a defense in depth security strategy?
Uses multiple redundant defenses to protect your AWS accounts, workloads, data, and assets.
How do you protect data at rest?
Encrypt with AWS Key Management Service (AWS KMS)
How do you protect data in transit?
1) AWS Certificate Manager (ACM) 2)AWS Private Certificate Authority (AWS Private CA).
Amazon service for identity and access management
AWS Identity and Access Management (IAM).
AWS application protection services
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
Infrastructure protection services
AWS Identity and Access Management (IAM)
IAM user groups and network access control lists (network ACLs)
AWS services that provide network and edge protection
Amazon Virtual Private Cloud (Amazon VPC)
AWS WAF
Threat detection and incident response services
AWS Security Hub
Amazon GuardDuty
What is Data logging?
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
What are prompt injections?
In these attacks, adversaries attempt to manipulate the input prompts of generative AI models to generate malicious or undesirable content
The Open Web Application Security Project (OWASP)
Industry standard list of the top 10 vulnerabilities that can impact a generative AI LLM system
The Open Web Application Security Project (OWASP) Top 10
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
What does AWS Security Hub provide?
a single dashboard to view all security findings, and to create and run automated playbooks.
What does AWS Key management service (KMS) do?
AWS KMS encrypts data and gives customers the choice and control of using AWS managed keys or customer-managed keys to protect their data.
What is Amazon GuardDuty?
A threat detection service that monitors for suspicious activity and unauthorized behavior to protect AWS accounts, workloads, and data
What is AWS Shield Advanced?
protect workloads against Distributed Denial of Service (DDoS) events. AWS Shield Advanced includes AWS WAF and AWS Firewall Manager.
What is cataloging?
the systematic organization and documentation of the datasets, models, and other resources used in the development of a generative AI system.
What is Amazon Inspector?
an automated vulnerability management service that continually scans AWS workloads for software vulnerabilities and unintended network exposure.
What is Amazon Detective?
streamlines the investigative process and helps security teams conduct faster and more effective forensic investigations.
What are model cards?
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
Data lineage
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.
Prompt Injection
Influencing the outputs by embedding specific instructions within the prompts themselves
Exposure
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.
5 types of machine learning
1) Supervised
2) Unsupervised
3) Semi-Supervised (small amount of labeled data and large amount of unlabeled data)
4) Reinforcement Learning
5) Deep Learning
What is AWS Artifact?
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