Related papers: VIGIL: Defending LLM Agents Against Tool Stream In…

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model (LLM)-based systems. We present PromptScreen, an efficient and systematically evaluated defense architecture that mitigates these threats…

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…

Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to their strong instruction-following capabilities and…

Large Language Models (LLMs) are vulnerable to prompt injection attacks, and several defenses have recently been proposed, often claiming to mitigate these attacks successfully. However, we argue that existing studies lack a principled…

LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which…

Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these…

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…

Tool-Based Agent Systems (TBAS) allow Language Models (LMs) to use external tools for tasks beyond their standalone capabilities, such as searching websites, booking flights, or making financial transactions. However, these tools greatly…

Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already…

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Large Language Models (LLMs) are combined with tools to create powerful LLM agents that provide a wide range of services. Unlike traditional software, LLM agent's behavior is determined at runtime by natural language prompts from either…

Despite advances in improving large language model (LLM) to refuse to answer malicious instructions, widely used LLMs remain vulnerable to jailbreak attacks where attackers generate instructions with distributions differing from safety…

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially…

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…

The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results…