相关论文: FLIRT: Feedback Loop In-context Red Teaming

Autonomous web agents such as \textbf{OpenClaw} are rapidly moving into high-impact real-world workflows, but their security robustness under live network threats remains insufficiently evaluated. Existing benchmarks mainly focus on static…

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}…

The rapid growth of Large Language Models (LLMs) presents significant privacy, security, and ethical concerns. While much research has proposed methods for defending LLM systems against misuse by malicious actors, researchers have recently…

Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4. These LLM-based chatbots encode the potential biases while retaining disparities that…

Prompting interfaces allow users to quickly adjust the output of generative models in both vision and language. However, small changes and design choices in the prompt can lead to significant differences in the output. In this work, we…

Diffusion models for text-to-image (T2I) synthesis, such as Stable Diffusion (SD), have recently demonstrated exceptional capabilities for generating high-quality content. However, this progress has raised several concerns of potential…

We introduce a multi-faceted automated red teaming framework in which the goal is to generate multi-modal adversarial conversations that would break a target model and introduce various expansions that would result in more effective and…

We introduce WildTeaming, an automatic LLM safety red-teaming framework that mines in-the-wild user-chatbot interactions to discover 5.7K unique clusters of novel jailbreak tactics, and then composes multiple tactics for systematic…

Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such…

Red teaming has evolved from its origins in military applications to become a widely adopted methodology in cybersecurity and AI. In this paper, we take a critical look at the practice of AI red teaming. We argue that despite its current…

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…

Generative Artificial Intelligence (GenAI) is becoming ubiquitous in our daily lives. The increase in computational power and data availability has led to a proliferation of both single- and multi-modal models. As the GenAI ecosystem…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

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…

The rapid proliferation of multimodal generative models has sparked critical discussions on their reliability, fairness and potential for misuse. While text-to-image models excel at producing high-fidelity, user-guided content, they often…

Text-to-image models have recently made significant advances in generating realistic and semantically coherent images, driven by advanced diffusion models and large-scale web-crawled datasets. However, these datasets often contain…

This paper investigates the challenging task of detecting backdoored text-to-image models under black-box settings and introduces a novel detection framework BlackMirror. Existing approaches typically rely on analyzing image-level…

Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating…

Red-teaming is a core part of the infrastructure that ensures that AI models do not produce harmful content. Unlike past technologies, the black box nature of generative AI systems necessitates a uniquely interactional mode of testing, one…

Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These attacks,…