Related papers: Proteus: A Self-Evolving Red Team for Agent Skill …

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…

AI agent development relies heavily on natural language prompting to define agents' tasks, knowledge, and goals. These prompts are interpreted by Large Language Models (LLMs), which govern agent behavior. Consequently, agentic performance…

In recent years, AI red teaming has emerged as a practice for probing the safety and security of generative AI systems. Due to the nascency of the field, there are many open questions about how red teaming operations should be conducted.…

Current test-time scaling (TTS) techniques enhance large language model (LLM) performance by allocating additional computation at inference time, yet they remain insufficient for agentic settings, where actions directly interact with…

Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been systematically stress-tested against deception strategies. We…

Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-driven capability sharing. However, despite their rapid…

Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…

Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point…

What should a developer inspect before deploying an LLM agent: the model, the tool code, the deployment configuration, or all three? In practice, many security failures in agent systems arise not from model weights alone, but from the…

Evolving attacks are a critical challenge for the long-term success of Network Intrusion Detection Systems (NIDS). The rise of these changing patterns has exposed the limitations of traditional network security methods. While…

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

Agent skills extend large language model (LLM) agents with reusable, program-like modules that define triggering conditions, procedural logic, and tool interactions. As these skills proliferate in public marketplaces, it is unclear what…

LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for…

The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models…

CTI-REALM (Cyber Threat Real World Evaluation and LLM Benchmarking) is a benchmark designed to evaluate AI agents' ability to interpret cyber threat intelligence (CTI) and develop detection rules. The benchmark provides a realistic…

LLM-based agents are increasingly used for cybersecurity tasks, but most existing systems rely on fixed, human-designed scaffolds that struggle to adapt across diverse targets and failure modes. We introduce \textsc{CyberEvolver}, a…

As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and…

Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient for modern organizations. While red teaming has long been recognized as an effective method…

As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial. While current red teaming approaches have made strides in assessing LLM vulnerabilities, they often rely heavily on human input and…