Related papers: When AIOps Become "AI Oops": Subverting LLM-driven…
The rapid expansion of the Internet of Things (IoT) has raised increasing concern about targeted cyber attacks. Previous research primarily focused on static Intrusion Detection Systems (IDSs), which employ offline training to safeguard IoT…
Machine Learning (ML) has become a fast-growing, trending approach in solution development in practice. Deep Learning (DL) which is a subset of ML, learns using deep neural networks to simulate the human brain. It trains machines to learn…
Today's AI agents are built on large language models (LLMs) equipped with tools to access and modify external environments, such as corporate file systems, API-accessible platforms and websites. AI agents offer the promise of automating…
The interactive nature of Large Language Models (LLMs), which closely track user data and context, has prompted users to share personal and private information in unprecedented ways. Even when users opt out of allowing their data to be used…
Automating cloud configuration and deployment remains a critical challenge due to evolving infrastructures, heterogeneous hardware, and fluctuating workloads. Existing solutions lack adaptability and require extensive manual tuning, leading…
As researchers continue to optimize AI agents for more effective task execution within operating systems, they often overlook a critical security concern: the ability of these agents to detect "impostors" within their environment. Through…
Despite the transformative impact of Artificial Intelligence (AI) across various sectors, cyber security continues to rely on traditional static and dynamic analysis tools, hampered by high false positive rates and superficial code…
As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be…
Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is…
The most valuable asset of any cloud-based organization is data, which is increasingly exposed to sophisticated cyberattacks. Until recently, the implementation of security measures in DevOps environments was often considered optional by…
The rapid evolution of mobile networks from 5G to 6G has necessitated the development of autonomous network management systems, such as Zero-Touch Networks (ZTNs). However, the increased complexity and automation of these networks have also…
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…
This research paper explores the privacy and security threats posed to an Agentic AI system with direct access to database systems. Such access introduces significant risks, including unauthorized retrieval of sensitive information,…
The emergence of Large Language Models (LLMs) has significantly advanced solutions across various domains, from political science to software development. However, these models are constrained by their training data, which is static and…
The reliance of mobile GUI agents on Multimodal Large Language Models (MLLMs) introduces a severe privacy vulnerability: screenshots containing Personally Identifiable Information (PII) are often sent to untrusted, third-party routers.…
System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…
Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with…
Artificial intelligence (AI) and machine learning (ML) have become increasingly vital in the development of novel defense and intelligence capabilities across all domains of warfare. An adversarial AI (A2I) and adversarial ML (AML) attack…
AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer…
Due to the wide adoption of IoT/CPS systems, embedded devices(IoT frontends) become increasingly connected and mission-critical, which in turn has attracted advanced attacks (e.g., control-flow hijacks and data-only attacks). Unfortunately,…