mlsanityData to 14 Oct 2026

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

arXiv 2508.20307 ↗First posted 27 Aug 2025cs.CR cs.AIcited by 0

Not on the map. Why?

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.

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

20 of 42 references.

References · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  6. 2022Red Teaming Language Models with Language Modelscited by 1,026
  7. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  8. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  9. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
  10. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 246
  11. 2024Exploiting LLM Quantizationcited by 65
  12. 2022"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practicecited by 56
8 more
  1. 2020Hermes Attack: Steal DNN Models with Lossless Inference Accuracycited by 41
  2. 2023Label Poisoning is All You Needcited by 29
  3. 2021Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomescited by 19
  4. 2021Stealthy Backdoors as Compression Artifactscited by 18
  5. 2023Towards more Practical Threat Models in Artificial Intelligence Securitycited by 17
  6. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
  7. 2024Concept-ROT: Poisoning Concepts in Large Language Models with Model Editingcited by 8
  8. 2023Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Personscited by 4

Built on by

Not cited yet.