Related papers: Contextual Agent Security: A Policy for Every Purp…
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…
Access to resources by users may need to be granted only upon certain conditions and contexts, perhaps particularly in cyber-physical settings. Unfortunately, creating and modifying context-sensitive access control solutions in dynamic…
Software tends to be highly configurable, but most applications are hardly context aware. For example, a web browser provides many settings to configure printers and proxies, but nevertheless it is unable to dynamically adapt to a new…
The operational efficacy of large language models relies heavily on their inference-time context. This has established Context Engineering (CE) as a formal discipline for optimizing these inputs. Current CE methods rely on manually crafted…
While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objective) has thus far hindered their use in critical applications…
Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an…
As a result of the phenomenal proliferation of modern mobile Internet-enabled devices and the widespread utilization of wireless and cellular data networks, mobile users are increasingly requiring services tailored to their current context.…
Digital agents capable of automating complex computer tasks have attracted considerable attention due to their immense potential to enhance human-computer interaction. However, existing agent methods exhibit deficiencies in their…
In today's dynamic ICT environments, the ability to control users' access to resources becomes ever important. On the one hand, it should adapt to the users' changing needs; on the other hand, it should not be compromised. Therefore, it is…
When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it…
We focus on the problem of designing an artificial agent (AI), capable of assisting a human user to complete a task. Our goal is to guide human users towards optimal task performance while keeping their cognitive load as low as possible.…
In this work we present the first holistic survey of the agentic security landscape, structuring the field around three fundamental pillars: Applications, Threats, and Defenses. We provide a comprehensive taxonomy of over 160 papers,…
AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…
Because of the growing interest for mobile device and pervasive applications deployed on cloud computing, the providing of intelligent and ubiquitous context-aware applications that take into account the user's context is one of the main…
We are interested in the problem of multiagent systems development for risk detecting and emergency response in an uncertain and partially perceived environment. The evaluation of the current situation passes by three stages inside the…
This paper proposes a new privacy-enhancing, context-aware user authentication system, ConSec, which uses a transformation of general location-sensitive data, such as GPS location, barometric altitude and noise levels, collected from the…
Investigating efficiently the data collected from a system's activity can help to detect malicious attempts and better understand the context behind past incident occurrences. Nowadays, several solutions can be used to monitor system…
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…
Traditional static cybersecurity models often struggle with scalability, real-time detection, and contextual responsiveness in the current digital product ecosystems which include cloud services, application programming interfaces (APIs),…
Computer Use Agents (CUAs), autonomous systems that interact with software interfaces via browsers or virtual machines, are rapidly being deployed in consumer and enterprise environments. These agents introduce novel attack surfaces and…