Chapter 6 · 2026
Threats and vulnerabilities in artificial intelligence and agentic AI models
Petar Radanliev, Omar Santos, Carsten Maple
Abstract
Adversarial robustness in artificial intelligence is commonly defined in terms of input-level perturbations applied to static models. This study reconceptualises adversarial vulnerability for artificial and agentic AI systems by extending the threat model to autonomy, self-governance, and closed-loop decision-making, where behaviour unfolds dynamically through feedback and control. We develop a system-level analytical framework that formalises adversarial risk across perceptual, cognitive, and executive layers. The analysis is grounded in a PRISMA-compliant systematic literature review, bibliometric mapping, and targeted empirical validation.
Topics
Adversarial AIAgentic AISecurityVulnerabilitiesThreat ModelingAutonomySelf-governanceDecision-making
Relevance Scores
Long-Horizon Score85
Enterprise Score80
Completeness75
Paper Info
Year2026
Venue
Type
ChapterCh. 6
Authors3
Zone III Analysis
Frameworks
Related Papers
Reflexion: Language Agents with Verbal Reinforcement Le…
2023 · Ch.1
AgentBench: Evaluating LLMs as Agents
2023 · Ch.1
Semantic Uncertainty: Linguistic Invariances for Uncert…
2023 · Ch.3
LLM-as-a-Judge: Large Language Models as Evaluators
2023 · Ch.5
View all Chapter 6 papers →