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

arXiv: https://arxiv.org/abs/2508.20307 · HTML: https://mlsanity.com/paper/2508.20307/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks](https://mlsanity.com/paper/1911.07135/) (2019)
- [Exploiting LLM Quantization](https://mlsanity.com/paper/2405.18137/) (2024)
- ["Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice](https://mlsanity.com/paper/2212.14315/) (2022)
- [Hermes Attack: Steal DNN Models with Lossless Inference Accuracy](https://mlsanity.com/paper/2006.12784/) (2020)
- [Label Poisoning is All You Need](https://mlsanity.com/paper/2310.18933/) (2023)
- [Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes](https://mlsanity.com/paper/2110.13541/) (2021)
- [Stealthy Backdoors as Compression Artifacts](https://mlsanity.com/paper/2104.15129/) (2021)
- [Towards more Practical Threat Models in Artificial Intelligence Security](https://mlsanity.com/paper/2311.09994/) (2023)
- [A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective](https://mlsanity.com/paper/2311.16065/) (2023)
- [Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing](https://mlsanity.com/paper/2412.13341/) (2024)
- [Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons](https://mlsanity.com/paper/2301.03118/) (2023)

## Abstract (arXiv)

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.