Related papers: AEGIS: No Tool Call Left Unchecked -- A Pre-Execut…
AI Accelerator (AIA) are specialized hardware e.g., Tensor Processing Unit (TPU), that enable optimal and efficient execution of AI applications and on-device inference. The growing demand for AI applications has led to the widespread…
AI agents can autonomously perform tasks and, often without explicit user consent, collect or disclose users' sensitive local data, which raises serious privacy concerns. Although AI agents' privacy policies describe their intended data…
LLM agents increasingly act on external systems, yet tool effects are immediate. Under failures, speculation, or contention, losing branches can leak unintended side effects with no safe rollback. We introduce Atomix, a runtime that…
AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make…
Leading AI developers and startups are increasingly deploying agentic AI systems that can plan and execute complex tasks with limited human involvement. However, there is currently no structured framework for documenting the technical…
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…
Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…
AI agents have significant potential to reshape cybersecurity, making a thorough assessment of their capabilities critical. However, existing evaluations fall short, because they are based on small-scale benchmarks and only measure static…
Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent…
As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…
Large language model based multi-agent systems (MAS) have unlocked significant advancements in tackling complex problems, but their increasing capability introduces a structural fragility that makes them difficult to debug. A key obstacle…
An auditor instructs an AI assistant: "open each file individually using the Read tool -- no scripts, no agents." The AI replies "Yes" -- then issues a single batched call summarizing all fifty files at once. We call this the Compliance…
As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between…
Large language models are increasingly used as natural-language interfaces to enterprise software, but their direct use as system operators remains unsafe. Model errors can propagate into unauthorized actions, malformed requests,…
Artificial Intelligence (AI) has transformed robotics, healthcare, industry, and scientific discovery, yet a major frontier may lie beyond Earth. Space exploration and settlement offer vast environments and resources, but impose constraints…
Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation practices where the AI…
AI audits are an increasingly popular mechanism for algorithmic accountability; however, they remain poorly defined. Without a clear understanding of audit practices, let alone widely used standards or regulatory guidance, claims that an AI…
Current AI-assisted engineering workflows lack a built-in mechanism to maintain task-level verification and regulatory traceability at machine-speed delivery. Agile V addresses this gap by embedding independent verification and audit…
Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and uncontrolled tool invocation -- that existing guardrails fail to address systematically.…
Autonomous and intelligent systems (AIS) facilitate a wide range of beneficial applications across a variety of different domains. However, technical characteristics such as unpredictability and lack of transparency, as well as potential…