Related papers: Agent Tools Orchestration Leaks More: Dataset, Ben…
AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a…
Progress in scientific discovery is rarely the result of a single "Eureka" moment, but is rather the product of hundreds of scientists incrementally working together toward a common goal. While existing agent workflows are capable of…
As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…
Medical AI agents increasingly use external tools for diagnosis, treatment recommendation, and evidence retrieval, yet most existing approaches assume that task-appropriate tools are reliable within their intended scope. This assumption is…
LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…
Machine learning models are known to memorize the unique properties of individual data points in a training set. This memorization capability can be exploited by several types of attacks to infer information about the training data, most…
The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one…
Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify…
In this study, we introduce the concept of OKR-Agent designed to enhance the capabilities of Large Language Models (LLMs) in task-solving. Our approach utilizes both self-collaboration and self-correction mechanism, facilitated by…
Communication topology is a critical factor in the utility and safety of LLM-based multi-agent systems (LLM-MAS), making it a high-value intellectual property (IP) whose confidentiality remains insufficiently studied. Existing topology…
As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coordination framework…
LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…
Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applications. Yet an overlooked threat is Reasoning-Level…
LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of…
How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…
SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sensitive information, fine-tune on proprietary recordings, or both. We identify and…
Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the…
Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…
Tool invocation is a core capability of agentic systems, yet failures often arise not from individual tool calls but from how multiple tools are organized and executed together. Existing approaches tightly couple tool execution with…
Large language models are powerful generalists, yet solving deep and complex problems such as those of the Humanity's Last Exam (HLE) remains both conceptually challenging and computationally expensive. We show that small orchestrators…