Related papers: Enforcing Benign Trajectories: A Behavioral Firewa…
As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural…
AI coding agents spend a substantial fraction of their tool calls on undirected codebase exploration. We investigate whether providing agents with formal architecture descriptors can reduce this navigational overhead. We present three…
Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…
Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic…
This paper presents a framework for converting wireless signals into structured datasets, which can be fed into machine learning algorithms for the detection of active eavesdropping attacks at the physical layer. More specifically, a…
The trust-based nature of Border Gateway Protocol (BGP) makes it vulnerable to disruptions like prefix hijacking and misconfigurations, threatening routing stability. Traditional detection relies on manual inspection with limited…
Automated analysis methods are crucial aids for monitoring and defending a network to protect the sensitive or confidential data it hosts. This work introduces a flexible, powerful, and unsupervised approach to detecting anomalous behavior…
The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive…
As a rapidly growing cyber-physical platform, Autonomous Vehicles (AVs) are encountering more security challenges as their capabilities continue to expand. In recent years, adversaries are actively targeting the perception sensors of…
Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…
Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The harmful…
A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while the task still completes. We call this overeager behavior: the prompt is not adversarial and…
A computational workflow, also known as workflow, consists of tasks that must be executed in a specific order to attain a specific goal. Often, in fields such as biology, chemistry, physics, and data science, among others, these workflows…
The transition of Large Language Models (LLMs) from passive code generators to autonomous agents introduces significant safety risks, specifically regarding destructive commands and inconsistent system states. Existing commercial solutions…
Web agents, powered by large language models (LLMs), are increasingly deployed to automate complex web interactions. The rise of open-source frameworks (e.g., Browser Use, Skyvern-AI) has accelerated adoption, but also broadened the attack…
Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…
Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…
Large-scale networked multi-agent systems increasingly underpin critical infrastructure, yet their collective behavior can drift toward undesirable emergent norms such as collusion, resource hoarding, and implicit unfairness. We present the…
Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to…
Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies…