Related papers: Cuckoo Attack: Stealthy and Persistent Attacks Aga…

As LLM-based agents become increasingly prevalent, backdoors can be implanted into agents through user queries or environment feedback, raising critical concerns regarding safety vulnerabilities. However, backdoor attacks are typically…

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

This technical brief introduces Deep Agent, an advanced autonomous AI system designed to manage complex multi-phase tasks through a novel hierarchical task management architecture. The system's foundation is built on our Hierarchical Task…

Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were first discovered by Preamble, Inc. in May 2022 and responsibly…

In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts. Despite its promising performance, crafted…

Artificial intelligence (AI) copilots are increasingly integrated into enterprise cybersecurity platforms to assist analysts in threat detection, triage, and remediation. However, the effectiveness of these systems depends not only on the…

Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered at inference. Existing backdoor attack methods typically…

The gossip-based distributed algorithms are widely used to solve decentralized optimization problems in various multi-agent applications, while they are generally vulnerable to data injection attacks by internal malicious agents as each…

High-assurance security systems require strong isolation from the untrusted world to protect the security-sensitive or privacy-sensitive data they process. Existing regulations impose that such systems must execute in a trustworthy…

Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the…

Attributing cyberattacks remains a central challenge in modern cybersecurity, particularly within denied environments where defenders have limited visibility into attacker infrastructure and are restricted by legal or operational rules of…

This article surveys Cognitive Edge Computing as a practical and methodical pathway for deploying reasoning-capable Large Language Models (LLMs) and autonomous AI agents on resource-constrained devices at the network edge. We present a…

Large Language Models (LLMs) deployed in enterprise settings (e.g., as Microsoft 365 Copilot) face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually…

Defense mechanisms against network-level attacks are commonly based on the use of cryptographic techniques, such as message authentication codes that provide data integrity guarantees. However, such mechanisms require significant resources,…

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…

The adversarial model presented by trusted execution environments (TEEs) has prompted researchers to investigate unusual attack vectors. One particularly powerful class of controlled-channel attacks abuses page-table modifications to…

In recent years, edge computing has emerged as a promising technology due to its unique feature of real-time computing and parallel processing. They provide computing and storage capacity closer to the data source and bypass the distant…

AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…

Cloud applications expose - besides service endpoints - also potential or actual vulnerabilities. Therefore, cloud security engineering efforts focus on hardening the fortress walls but seldom assume that attacks may be successful. At least…

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…