Related papers: PAuth - Precise Task-Scoped Authorization For Agen…
In past years, we have been dedicated to automating user acceptance testing (UAT) process of WeChat Pay, one of the most influential mobile payment applications in China. A system titled XUAT has been developed for this purpose. However,…
Large Language Model (LLM) -in-the-loop applications have been shown to effectively interpret the human user's commands, make plans, and operate external tools/systems accordingly. Still, the operation scope of the LLM agent is limited to…
Large Language Model (LLM) agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe security risks, particularly direct and indirect prompt…
Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance on dynamic web content, however, makes them vulnerable to prompt injection attacks:…
Open-source software OSS is widely adopted in enterprise settings, but standalone tools often lack native support for protocols like SAML or OIDC, creating a critical security integration gap. This paper introduces and formalizes the Auth…
Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites…
The pervasiveness of wireless communication recently gave mobile ad hoc networks (MANET) a significant researchers' attention, due to its innate capabilities of instant communication in many time and mission critical applications. However,…
Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state implicit and making…
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.…
Advanced AI assistants combine frontier LLMs and tool access to autonomously perform complex tasks on behalf of users. While the helpfulness of such assistants can increase dramatically with access to user information including emails and…
AI agents equipped with tool-calling capabilities are susceptible to Indirect Prompt Injection (IPI) attacks. In this attack scenario, malicious commands hidden within untrusted content trick the agent into performing unauthorized actions.…
Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…
Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…
Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhanced ability to interact with external systems and process…
Privacy leakage in AI-based decision processes poses significant risks, particularly when sensitive information can be inferred. We propose a formal framework to audit privacy leakage using abductive explanations, which identifies minimal…
As the "agentic web" takes shape-billions of AI agents (often LLM-powered) autonomously transacting and collaborating-trust shifts from human oversight to protocol design. In 2025, several inter-agent protocols crystallized this shift,…
This study investigates malicious AI Assistants' manipulative traits and whether the behaviours of malicious AI Assistants can be detected when interacting with human-like simulated users in various decision-making contexts. We also examine…
The rapid advancement of Generative AI has catalyzed the emergence of autonomous AI agents, presenting unprecedented challenges for enterprise computing infrastructures. Current enterprise API architectures are predominantly designed for…
Lightweight authentication is essential for resource-constrained Internet-of-Things (IoT). Implementable with low resource and operable with low power, Physical Unclonable Functions (PUFs) have the potential as hardware primitives for…