Related papers: Red-teaming Activation Probes using Prompted LLMs

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…

Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating…

Applications that use Large Language Models (LLMs) are becoming widespread, making the identification of system vulnerabilities increasingly important. Automated Red Teaming accelerates this effort by using an LLM to generate and execute…

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current…

Automated red teaming is an effective method for identifying misaligned behaviors in large language models (LLMs). Existing approaches, however, often focus primarily on improving attack success rates while overlooking the need for…

As LLMs gain persuasive capabilities through extended dialogues, they create new opportunities for studying adversarial conversational behavior in extended interaction settings that traditional single-turn safety evaluations fail to…

Automated red-teaming has emerged as a scalable approach for auditing Large Language Models (LLMs) prior to deployment, yet existing approaches lack mechanisms to efficiently adapt to model-specific vulnerabilities at inference. We…

Large language models (LLMs) hold great potential for many natural language applications but risk generating incorrect or toxic content. To probe when an LLM generates unwanted content, the current paradigm is to recruit a \textit{red team}…

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

The shift toward interacting with frozen, "black-box" Large Language Models (LLMs) has transformed prompt engineering from a heuristic exercise into a critical optimization challenge. We propose a Reinforcement Learning (RL) framework for…

A red team simulates adversary attacks to help defenders find effective strategies to defend their systems in a real-world operational setting. As more enterprise systems adopt AI, red-teaming will need to evolve to address the unique…

We describe PromptBoosting, a query-efficient procedure for building a text classifier from a neural language model (LM) without access to the LM's parameters, gradients, or hidden representations. This form of "black-box" classifier…

Large Language Models (LLMs) are vulnerable to jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires a time-consuming search for adversarial prompts, whereas automatic adversarial…

While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in…

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on…

As the practicality of Artificial Intelligence (AI) and Machine Learning (ML) based techniques grow, there is an ever increasing threat of adversarial attacks. There is a need to red team this ecosystem to identify system vulnerabilities,…

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test…

The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive…

Red-teaming has been a widely adopted way to evaluate the harmfulness of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful agent disregarding the harmfulness of the query. Existing…

We introduce meta-prompting, an effective scaffolding technique designed to enhance the functionality of language models (LMs). This approach transforms a single LM into a multi-faceted conductor, adept at managing and integrating multiple…