Related papers: Poster: ClawdGo: Endogenous Security Awareness Tra…
Advanced Persistent Threats (APTs) are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit…
Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial training has proven to be one of the most promising methods to reliably improve robustness against such…
Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and uncontrolled tool invocation -- that existing guardrails fail to address systematically.…
The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk awareness and transparency in risk diagnosis. To introduce…
The increasing instances of advanced attacks call for a new defense paradigm that is active, autonomous, and adaptive, named as the \texttt{`3A'} defense paradigm. This chapter introduces three defense schemes that actively interact with…
Adversarial robustness of deep models is pivotal in ensuring safe deployment in real world settings, but most modern defenses have narrow scope and expensive costs. In this paper, we propose a self-supervised method to detect adversarial…
Defending computer networks from cyber attack requires timely responses to alerts and threat intelligence. Decisions about how to respond involve coordinating actions across multiple nodes based on imperfect indicators of compromise while…
Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or…
Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working memory through their context window, which stores interaction…
The highest level in the Endsley situation awareness model is called projection when the status of elements in the environment in the near future is predicted. In cybersecurity situation awareness, the projection for an Advanced Persistent…
While Large Language Models (LLMs) have achieved remarkable capabilities, they unintentionally memorize sensitive data, posing critical privacy and security risks. Machine unlearning is pivotal for mitigating these risks, yet existing…
Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…
We present SuperLocalMemory, a local-first memory system for multi-agent AI that defends against OWASP ASI06 memory poisoning through architectural isolation and Bayesian trust scoring, while personalizing retrieval through adaptive…
A significant challenge for autonomous cyber defence is ensuring a defensive agent's ability to generalise across diverse network topologies and configurations. This capability is necessary for agents to remain effective when deployed in…
Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…
We introduce Embedded Safety-Aligned Intelligence (ESAI), a theoretical framework for multi-agent reinforcement learning that embeds alignment constraints directly into agents internal representations using differentiable internal alignment…
AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task execution, and multimodal interactions through large language models (LLMs). However, these…
Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…
Artificial intelligence (AI) systems are being readily and rapidly adopted, increasingly permeating critical domains: from consumer platforms and enterprise software to networked systems with embedded agents. While this has unlocked…
When combining Large Language Models (LLMs) with autonomous agents, used in network monitoring and decision-making systems, this will create serious security issues. In this research, the MAESTRO framework consisting of the seven layers…