← Back ◬ AI & Machine Learning May 19, 2026

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI

arXiv Security Archived May 19, 2026 ✓ Full text saved

arXiv:2605.16471v1 Announce Type: new Abstract: Generative AI systems are increasingly used not only to produce content but also to retrieve data, invoke tools, and execute actions. This work examines the security and safety implications of that shift across content-level, model-level, and agentic threats. We analyze how attacker access requirements, system autonomy, and the scope of potential harm change as models move from generating artifacts to executing operations through tool chains and ex

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Cryptography and Security [Submitted on 15 May 2026] From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI Zelin Zhang, Qi Li, Jie Cao, Lingshuang Liu, Jianbing Ni Generative AI systems are increasingly used not only to produce content but also to retrieve data, invoke tools, and execute actions. This work examines the security and safety implications of that shift across content-level, model-level, and agentic threats. We analyze how attacker access requirements, system autonomy, and the scope of potential harm change as models move from generating artifacts to executing operations through tool chains and external APIs. We then assess technical countermeasures including detection, watermarking, alignment, and emerging agentic safeguards, and show that several depend on forms of institutional coordination that current governance arrangements do not yet provide. Across the cases examined, capability deployment and attack-surface expansion repeatedly outpace defensive responses as systems move from generating content to executing real-world actions. Comments: Accepted by Journal of Information and Intelligence (JII) Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2605.16471 [cs.CR] (or arXiv:2605.16471v1 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2605.16471 Focus to learn more Submission history From: Qi Li [view email] [v1] Fri, 15 May 2026 13:53:02 UTC (155 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev | next > new | recent | 2026-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes