Related papers: Cuckoo Attack: Stealthy and Persistent Attacks Aga…
Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly…
Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain…
A prompt injection attack aims to inject malicious instruction/data into the input of an LLM-Integrated Application such that it produces results as an attacker desires. Existing works are limited to case studies. As a result, the…
This study introduces an innovative approach to automating Cyber Threat Intelligence (CTI) processes in industrial environments by leveraging Microsoft's AI-powered security technologies. Historically, CTI has heavily relied on manual…
Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more…
AI coding assistants are widely used for tasks like code generation. These tools now require large and complex contexts, automatically sourced from various origins$\unicode{x2014}$across files, projects, and…
This work explores injection attacks against password managers. In this setting, the adversary (only) controls their own application client, which they use to "inject" chosen payloads to a victim's client via, for example, sharing…
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…
The authentication field is evolving towards mechanisms able to keep users continuously authenticated without the necessity of remembering or possessing authentication credentials. While existing continuous authentication systems have…
The rapid growth of interest in quantum computing has brought about the need to secure these powerful machines against a range of physical attacks. As qubit counts increase and quantum computers achieve higher levels of fidelity, their…
Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…
Prompt injection is listed as the number-one vulnerability class in the OWASP Top 10 for LLM Applications that can subvert LLM guardrails, disclose sensitive data, and trigger unauthorized tool use. Developers are rapidly adopting…
Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering…
As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insufficient because privacy risks often arise after access is…
AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential…
The Model Context Protocol (MCP) replaces static, developer-controlled API integrations with more dynamic, user-driven agent systems, which also introduces new security risks. As MCP adoption grows across community servers and major…
Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation (RAG) allows…
Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process provides attackers with more opportunities to inject…
Cloud applications expose - beside service endpoints - also potential or actual vulnerabilities. And attackers have several advantages on their side. They can select the weapons, the point of time and the point of attack. Very often cloud…
Large language models (LLMs)-powered AI agents exhibit a high level of autonomy in addressing medical and healthcare challenges. With the ability to access various tools, they can operate within an open-ended action space. However, with the…