Related papers: Zero-Permission Manipulation: Can We Trust Large M…
Automated input generators are widely used for large-scale dynamic analysis of mobile apps. Such input generators must constantly choose which UI element to interact with and how to interact with it, in order to achieve high coverage with a…
Recently, applications powered by Large Language Models (LLMs) have made significant strides in tackling complex tasks. By harnessing the advanced reasoning capabilities and extensive knowledge embedded in LLMs, these applications can…
The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of foundation GUI agents spanning the full spectrum of sizes, including 2B, 8B, 32B,…
Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from…
Thanks to advances in large language models, a new type of software agent, the artificial intelligence (AI) agent, has entered the marketplace. Companies such as OpenAI, Google, Microsoft, and Salesforce promise their AI Agents will go from…
The rapid evolution of Artificial Intelligence (AI) and Large Language Models (LLMs) has opened up new opportunities in the area of cybersecurity, especially in the exploitation automation landscape and penetration testing. This study…
Mobile advertising dominates app monetization but introduces risks ranging from intrusive user experience to malware delivery. Existing detection methods rely either on static analysis, which misses runtime behaviors, or on heuristic UI…
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…
An intrusion detection system framework using mobile agents is a layered framework mechanism designed to support heterogeneous network environments to identify intruders at its best. Traditional computer misuse detection techniques can…
Modern web test suites rot. A UI refactor breaks locators, a timing change causes race conditions, and within weeks developers abandon the suite entirely. This paper presents an AI-driven autonomous testing framework that addresses these…
In the same way that generative models today conduct most of their training in a self-supervised fashion, how can agentic models conduct their training in a self-supervised fashion, interactively exploring, learning, and preparing to…
GUI agents have emerged as a powerful paradigm for automating interactions in digital environments, yet achieving both broad generality and consistently strong task performance remains challenging. In this report, we present UI-Venus-1.5, a…
Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…
AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…
Graphical user interface (GUI) agents have advanced rapidly but still struggle with complex tasks involving novel UI elements, long-horizon actions, and personalized trajectories. In this work, we introduce Instruction Agent, a GUI agent…
Agentification serves as a critical enabler of Edge General Intelligence (EGI), transforming massive edge devices into cognitive agents through integrating Large Language Models (LLMs) and perception, reasoning, and acting modules. These…
Smartphones with the platforms of applications are gaining extensive attention and popularity. The enormous use of different applications has paved the way to numerous security threats. The threats are in the form of attacks such as…
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It…
Autonomous agents powered by multimodal large language models have been developed to facilitate task execution on mobile devices. However, prior work has predominantly focused on atomic tasks -- such as shot-chain execution tasks and…
Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…