Related papers: AIRGuard: Guarding Agent Actions with Runtime Auth…
The AI Control research agenda aims to develop control protocols: safety techniques that prevent untrusted AI systems from taking harmful actions during deployment. Because human oversight is expensive, one approach is trusted monitoring,…
In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization to safeguard…
The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of users.…
Agentic AI shifts LLM serving from isolated prompt-generation requests to stateful, multi-turn executions that repeatedly invoke the model, call tools, and grow context over time. This paper characterizes ReAct-style agents from both the…
Large language models generate plausible code but cannot verify correctness. Existing multi-agent systems simulate execution or leave verification optional. We introduce execution-grounded verification as a first-class principle: every code…
Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…
The integration of Large Language Models (LLMs) into cybersecurity education for criminal justice professionals is currently hindered by the "statelessness" of reactive chatbots and the risk of hallucinations in high-stakes legal contexts.…
The rapid development of mobile GUI agents has stimulated growing research interest in long-horizon task automation. However, building agents for these tasks faces a critical bottleneck: the reliance on ever-expanding interaction history…
Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted with perceiving screen content and injecting inputs. However, their design operates under the implicit assumption of Visual…
Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…
AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., personal and financial information). This poses a serious risk to security and privacy.…
What should a developer inspect before deploying an LLM agent: the model, the tool code, the deployment configuration, or all three? In practice, many security failures in agent systems arise not from model weights alone, but from the…
Current large language model agent frameworks prioritize autonomy but lack the governability mechanisms required for enterprise deployment. High-risk write operations proceed without independent review, complex tasks lack acceptance…
In this paper we argue, drawing from the perspectives of cybersecurity and social psychology, that Internet-based manipulation of an individual or group reality using ambient tactical deception is possible using only software and changing…
Multi-Agent System is emerging as the \textit{de facto} standard for complex task orchestration. However, its reliance on autonomous execution and unstructured inter-agent communication introduces severe risks, such as indirect prompt…
Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…
We present QuadAgent, a training-free agent system for agile quadrotor flight guided by vision-language inputs. Unlike prior end-to-end or serial agent approaches, QuadAgent decouples high-level reasoning from low-level control using an…
Equipping LLM agents with real-world tools can substantially improve productivity. However, granting agents autonomy over tool use also transfers the associated privileges to both the agent and the underlying LLM. Improper privilege usage…
As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…
AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the agent's syscalls -- privileged operations with side effects on shared state -- yet today's safety…