Contents
What are the threats for distributed systems?
Security vulnerabilities dormant in a distributed system can be intentionally exploited or inadvertently triggered. The threats of exploitation or triggering are only potential, and materialize as an attack or an accident.
What are the example of distributed systems?
Telephone and cellular networks are also examples of distributed networks. Telephone networks have been around for over a century and it started as an early example of a peer to peer network. Cellular networks are distributed networks with base stations physically distributed in areas called cells.
What are the new considerations in threat modeling?
This document is divided into two sections: “Key New Considerations in Threat Modeling” focuses on new ways of thinking and new questions to ask when threat modeling AI/ML systems. Both data scientists and security engineers should review this as it will be their playbook for threat modeling discussions and mitigation prioritization.
How are adversarial samples used in threat modeling?
The adversarial sample can appear like random noise to human eyes but attackers have some knowledge of the target machine learning system to generate a white noise that is not random but is exploiting some specific aspects of the target model.
How is threat modeling used in machine learning?
This document is a deliverable of the AETHER Engineering Practices for AI Working Group and supplements existing SDL threat modeling practices by providing new guidance on threat enumeration and mitigation specific to the AI and Machine Learning space. It is intended to be used as a reference during security design reviews of the following:
Who are the data scientists in threat modeling?
This section is primarily targeted at data scientists who may need to implement specific threat mitigations as an output of the threat modeling/security review process.