Related papers: ClawLess: A Security Model of AI Agents

This paper presents a novel, structured decision support framework that systematically aligns diverse artificial intelligence (AI) agent architectures, reactive, cognitive, hybrid, and learning, with the comprehensive National Institute of…

The increasing integration of AI agents into cyber-physical systems (CPS) introduces new security risks that extend beyond traditional cyber or physical threat models. Recent advances in generative AI enable deepfake and semantic…

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across industries through intuitive language interfaces and continuous improvements in model…

AI agents that interact with their environments through tools enable powerful applications, but in high-stakes business settings, unintended actions can cause unacceptable harm, such as privacy breaches and financial loss. Existing…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

As ongoing research explores the ability of AI agents to be insider threats and act against company interests, we showcase the abilities of such agents to act against human well being in service of corporate authority. Building on Agentic…

This paper explores the potential of a multidisciplinary approach to testing and aligning artificial intelligence (AI), specifically focusing on large language models (LLMs). Due to the rapid development and wide application of LLMs,…

In the vast domain of cybersecurity, the transition from reactive defense to offensive has become critical in protecting digital infrastructures. This paper explores the integration of Artificial Intelligence (AI) into offensive…

As AI rapidly advances, the security risks posed by AI are becoming increasingly severe, especially in critical scenarios, including those posing existential risks. If AI becomes uncontrollable, manipulated, or actively evades safety…

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…

Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…

The interactive nature of Large Language Models (LLMs), which closely track user data and context, has prompted users to share personal and private information in unprecedented ways. Even when users opt out of allowing their data to be used…

This research paper explores the privacy and security threats posed to an Agentic AI system with direct access to database systems. Such access introduces significant risks, including unauthorized retrieval of sensitive information,…

The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces…

This paper presents a conceptual and operational framework for developing and operating safe and trustworthy AI agents based on a Three-Pillar Model grounded in transparency, accountability, and trustworthiness. Building on prior work in…

This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on…

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…