Related papers: ARGUS: Defending LLM Agents Against Context-Aware …

LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments, adversaries can copy and reuse these prompts with other…

Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer from over-defense -- falsely flagging benign inputs as…

Large language model (LLM)-based computer-use agents represent a convergence of AI and OS capabilities, enabling natural language to control system- and application-level functions. However, due to LLMs' inherent uncertainty issues,…

Prompt injection remains a major security risk for large language models. However, the efficacy of existing guardrail models in context-aware settings remains underexplored, as they often rely on static attack benchmarks. Additionally, they…

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…

Large language models (LLMs) are rapidly evolving from single-modal systems to multimodal LLMs and intelligent agents, significantly expanding their capabilities while introducing increasingly severe security risks. This paper presents a…

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static,…

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve…

LLM-based coding agents can generate functionally correct GPU kernels, yet their performance remains far below hand-optimized libraries on critical computations such as matrix multiplication, attention, and Mixture-of-Experts (MoE). Peak…

Large Language Models (LLMs) like GPT-4 have revolutionized natural language processing, showing remarkable linguistic proficiency and reasoning capabilities. However, their application in strategic multi-agent decision-making environments…

Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization to safeguard…

With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to…

Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated against human annotation. We introduce AgentProp-Bench, a 2,000-task benchmark with 2,300…

A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs)…

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…

Sensitive information leakage in code repositories has emerged as a critical security challenge. Traditional detection methods that rely on regular expressions, fingerprint features, and high-entropy calculations often suffer from high…

The advances made by Large Language Models (LLMs) have led to the pursuit of LLM agents that can solve intricate, multi-step reasoning tasks. As with any research pursuit, benchmarking and evaluation are key corner stones to efficient and…

Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf. While these agents offer powerful capabilities, their…