23 papers indexed here
Not the right person? Other researchers publish under this name.
A new scientific object – the Autonomous Recovery Efficiency Score (ARES) – is introduced – a quantitative measure of autonomous resilience, as well as a supporting foundation for future autonomous self-healing AI agentic infrastructure.
The speed of cloud computing and artificial intelligence, which have transformed the way software applications are designed and deployed. The cloud-based AI systems provide a scalable, adaptable, and cost-efficient solution to build intelligent systems capable of processing large amounts of data and running complicated...
Autonomous multi-agent artificial intelligence (AI) systems have emerged as a rapidly evolving field that revolutionizes the way autonomous systems can make decisions together, collaborate on tasks, and learn, thereby opening new paradigms for distributed decision-making, task execution, and adaptive learning. The comp...
This paper presents a meta-synthesis that draws together four constituent studies covering adversarial machine learning, AI-powered anomaly detection in cloud environments, automated vulnerability patching by multi-agent large language model (LLM) pipelines, and the broader landscape of securing AI systems across their...
While multi-agent LLM pipelines show real promise for legacy code specifically, since their capacity for autonomous context reconstruction and iterative, feedback-driven refinement directly addresses the sparse documentation and thin test coverage that define legacy environments, the literature to date has been validat...
The findings suggest that AI-powered anomaly detection significantly strengthens observability and security in cloud-based applications, enabling proactive threat mitigation and operational optimization in increasingly complex distributed environments.
A previously unstated class of adversarial input called a clean attack - an input that is syntactically correct, semantically consistent with the declared task context, consistent with all observable policy constraints and still has the goal of misguiding the agent away from the original operator goal - is identified a...
This paper synthesizes the findings of the five-paper AI Agent Security Series into a unified, formal, and falsifiable theory of autonomous agent security, and establishes three meta-theorems: the Component Insufficiency Theorem, the Dynamic Necessity Theorem, and the Interaction Irreducibility Theorem.
Securing AI systems is not a task any single discipline can accomplish alone; it requires sustained collaboration between machine learning researchers, cybersecurity professionals, and policymakers if AI technologies are to remain reliable, trustworthy, and resilient in adversarial environments.
A detailed overview of the security risks associated with adversarial attacks is offered, including evasion attacks carried out at inference time, data poisoning that corrupts the training process, backdoor insertion that hides dormant triggers inside a model, and model inversion that leaks private information back out...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
