Related papers: Trust No Tool: Evaluating and Defending LLM Agents…

Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under adversarial conditions such as prompt injection or memory poisoning. In deployment,…

Structured Outputs from current LLMs exhibit sporadic errors, hindering enterprise AI deployment. We present CONSTRUCT, a real-time uncertainty estimator that scores the trustworthiness of LLM Structured Outputs. Lower-scoring outputs are…

Large language models (LLMs) have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows, and taking higher-stakes actions based on untrusted inputs…

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platforms, e.g. robots and autonomous vehicles, to interpret visual scenes and execute natural…

Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, prompting a surge in their practical applications. However, concerns have arisen regarding the trustworthiness of LLMs outputs, particularly in…

Large language models (LLMs) now mediate many web-based mental-health, crisis, and other emotionally sensitive services, yet their psychosocial safety in these settings remains poorly understood and weakly evaluated. We present DialogGuard,…

As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful behaviors from LLMs, poses an ever increasing risk. Prompt injection attacks can cause LLMs to…

Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…

As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. However, the absence of…

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or APIs…

Ensuring AI safety is crucial as large language models become increasingly integrated into real-world applications. A key challenge is jailbreak, where adversarial prompts bypass built-in safeguards to elicit harmful disallowed outputs.…

As AI models progress beyond simple chatbots into more complex workflows, we draw ever closer to the event horizon beyond which AI systems will be utilized in autonomous, self-maintaining feedback loops. Any autonomous AI system will depend…

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…

TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These systems, which consist of multiple LLM-powered agents working…

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…

Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a…

We introduce AutoMonitor-Bench, the first benchmark designed to systematically evaluate the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes. AutoMonitor-Bench consists of 3,010 carefully annotated test…

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…