mlsanityData to 14 Oct 2026

AI Safety vs. AI Security: Demystifying the Distinction and Boundaries

arXiv 2506.18932 ↗First posted 21 Jun 2025cs.CY cs.AI cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

Artificial Intelligence (AI) is rapidly being integrated into critical systems across various domains, from healthcare to autonomous vehicles. While its integration brings immense benefits, it also introduces significant risks, including those arising from AI misuse. Within the discourse on managing these risks, the terms "AI Safety" and "AI Security" are often used, sometimes interchangeably, resulting in conceptual confusion. This paper aims to demystify the distinction and delineate the precise research boundaries between AI Safety and AI Security. We provide rigorous definitions, outline their respective research focuses, and explore their interdependency, including how security breaches can precipitate safety failures and vice versa. Using clear analogies from message transmission and building construction, we illustrate these distinctions. Clarifying these boundaries is crucial for guiding precise research directions, fostering effective cross-disciplinary collaboration, enhancing policy effectiveness, and ultimately, promoting the deployment of trustworthy AI systems.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 26 of its 51 references that are in the map. First posted on arXiv 21 Jun 2025.

Builds on

26 of 51 references.

References · 26

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  6. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  7. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  9. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  10. 2020Extracting Training Data from Large Language Modelscited by 2,189
  11. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  12. 2016Concrete Problems in AI Safetycited by 1,642
14 more
  1. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  2. 2019Natural Adversarial Examplescited by 1,408
  3. 2021Ethical and social risks of harm from Language Modelscited by 966
  4. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  5. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  6. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  7. 2020Artificial Intelligence, Values and Alignmentcited by 448
  8. 2024Improving Alignment and Robustness with Circuit Breakerscited by 322
  9. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  10. 2023An Overview of Catastrophic AI Riskscited by 222
  11. 2020Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claimscited by 165
  12. 2022Is Power-Seeking AI an Existential Risk?cited by 105
  13. 2015The social dilemma of autonomous vehiclescited by 48
  14. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2026When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agentscited by 14
  2. 2026Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system securitycited by 5
  3. 2025Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harmcited by 3
  4. 2025Mind the Gap! Pathways Towards Unifying AI Safety and Ethics Researchcited by 2
  5. 2026AI Assurance in UK Defence: Challenges in Operationalising JSP 936cited by 0