Related papers: Provably Secure Agent Guardrail
One of the most widespread framework for the management of access-control policies is Administrative Role Based Access Control (ARBAC). Several automated analysis techniques have been proposed to help maintaining desirable security…
Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that may trigger unsafe behaviors. Runtime safety guardrails,…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
Large foundation models are integrated into Computer Use Agents (CUAs), enabling autonomous interaction with operating systems through graphical user interfaces (GUIs) to perform complex tasks. This autonomy introduces serious security…
Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they introduce latency…
We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens,…
For decades, the security of digital interaction has rested on an unacknowledged economic constraint. Attackers faced a tradeoff between the fidelity of a deception and the scale at which it could be deployed. Convincing impersonation…
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:…
Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies,…
As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable controls. We introduce a regulatory machine learning framework that converts unstructured design…
Language models exhibit human-like cognitive vulnerabilities, such as emotional framing, that escape traditional behavioral alignment. We present CCS-7 (Cognitive Cybersecurity Suite), a taxonomy of seven vulnerabilities grounded in human…
Semantic communication (SemCom) redefines wireless communication from reproducing symbols to transmitting task-relevant semantics. However, this AI-native architecture also introduces new vulnerabilities, as semantic failures may arise from…
Large Language Model agents deployed in complex environments frequently encounter a conflict between maximizing goal achievement and adhering to safety constraints. This paper identifies a new concept called Agentic Pressure, which…
Generative AI systems are increasingly used not only to produce content but also to retrieve data, invoke tools, and execute actions. This work examines the security and safety implications of that shift across content-level, model-level,…
Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…
Our computing ecosystem is being transformed by two emerging paradigms: the increased deployment of agentic AI systems and advancements in quantum computing. With respect to agentic AI systems, one of the most critical problems is creating…
As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete deployment harms. In these settings, guardrail failures are no…
In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This…
Agentic AI systems plan, use tools, maintain state, and produce multi-step trajectories with external effects. Those properties create a governance problem that differs materially from single-turn generative AI: important risks emerge dur-…
Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilities unlock substantial practical value, they also introduce…