# Surveying the Operational Cybersecurity and Supply Chain Threat Landscape when Developing and Deploying AI Systems

## TL;DR

This survey highlights emerging cybersecurity and supply chain threats specific to AI systems, emphasizing the need for tailored security measures to address unique attack vectors and operational risks across the AI lifecycle.

## Contribution

It provides a comprehensive overview of novel cyber threats in AI development and deployment, emphasizing operational and supply chain risks often overlooked by traditional cybersecurity assessments.

## Key findings

- AI introduces new attack surfaces and objectives.
- Cyber attackers target AI outputs to manipulate system behavior.
- Awareness and tailored security frameworks are essential for AI resilience.

## Abstract

The rise of AI has transformed the software and hardware landscape, enabling powerful capabilities through specialized infrastructures, large-scale data storage, and advanced hardware. However, these innovations introduce unique attack surfaces and objectives which traditional cybersecurity assessments often overlook. Cyber attackers are shifting their objectives from conventional goals like privilege escalation and network pivoting to manipulating AI outputs to achieve desired system effects, such as slowing system performance, flooding outputs with false positives, or degrading model accuracy. This paper serves to raise awareness of the novel cyber threats that are introduced when incorporating AI into a software system. We explore the operational cybersecurity and supply chain risks across the AI lifecycle, emphasizing the need for tailored security frameworks to address evolving threats in the AI-driven landscape. We highlight previous exploitations and provide insights from working in this area. By understanding these risks, organizations can better protect AI systems and ensure their reliability and resilience.