Kumrashan Indranil Iyer

Artificial intelligence (AI) and data science models play a crucial role in critical sectors such as cybersecurity, healthcare, and finance, driving key insights and decision-making processes. However, as AI adoption grows, so does its exposure to emerging threats, particularly model poisoning attacks. In these attacks, adversaries stealthily manipulate training data to corrupt model behavior, either causing it to produce malicious outputs or rendering it ineffective against specific threats. This paper examines the methods and motivations behind data poisoning attacks, focusing on how adversaries compromise data pipelines, manipulate model performance, and evade detection. We also examine potential countermeasures and discuss ongoing research challenges that must be overcome to protect AI systems from these evolving threats.

The emergence of Agentic AI autonomous systems that can make and execute decisions without human intervention has presented new and complex challenges in cybersecurity. Traditional trust models and defense mechanisms are insufficient to handle these dynamic, intelligent threats. In this paper, we propose a novel Cognitive Trust Architecture (CTA) aimed at detecting, assessing, and mitigating agentic AI-driven cyber threats. We introduce an adaptive trust reasoning framework that continuously adjusts trust levels based on behavioral indicators, intent inference, and contextual analysis. Additionally, the framework incorporates autonomous adversary modeling to predict and counter potential attack strategies. By leveraging this approach, we demonstrate the efficacy of CTA in enhancing system integrity, reducing false positives in trust assessments, and improving resilience against evolving AI-driven adversaries. This work represents a significant advancement in applying cognitive trust as a proactive defense mechanism to counter intelligent, autonomous cyber threats.