Related papers: Security Considerations for Artificial Intelligenc…
We empirically evaluate whether AI systems are more effective at attacking or defending in cybersecurity. Using CAI (Cybersecurity AI)'s parallel execution framework, we deployed autonomous agents in 23 Attack/Defense CTF battlegrounds.…
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target…
Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…
AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous human supervision. This creates a problem no current infrastructure is equipped to solve: how do you identify,…
The complex and evolving threat landscape of frontier AI development requires a multi-layered approach to risk management ("defense-in-depth"). By reviewing cybersecurity and AI frameworks, we outline three approaches that can help identify…
The rapid advancement of Generative AI has catalyzed the emergence of autonomous AI agents, presenting unprecedented challenges for enterprise computing infrastructures. Current enterprise API architectures are predominantly designed for…
AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…
The rapid development of AI agents leads to a surge in communication demands. Alongside this rise, a variety of frameworks and protocols emerge. While these efforts demonstrate the vitality of the field, they also highlight increasing…
Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…
Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequate alignment or insufficient guardrails, it is architectural:…
AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where…
Cybersecurity has become one of the earliest adopters of agentic AI, as security operations centers increasingly rely on multi-step reasoning, tool-driven analysis, and rapid decision-making under pressure. While individual large language…
Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust and communication…
Security Operations Centers (SOCs) increasingly encounter difficulties in correlating heterogeneous alerts, interpreting multi-stage attack progressions, and selecting safe and effective response actions. This study introduces AgentSOC, a…
The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one…
The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive. Many researchers are concerned that AIs and AGIs will harm humans via intentional misuse (AI-misuse)…
To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…
Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as…
Large Language Model (LLM)-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for agentic system governance emphasize the need for users to…
AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and…