Related papers: Abusing Images and Sounds for Indirect Instruction…

Multi-modal visual understanding of images with prompts involves using various visual and textual cues to enhance the semantic understanding of images. This approach combines both vision and language processing to generate more accurate…

We describe a vulnerability in language models (LMs) trained with user feedback, whereby a single user can persistently alter LM knowledge and behavior given only the ability to provide prompts and upvote / downvote feedback on LM outputs.…

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

We propose a new class of signal injection attacks on microphones by physically converting light to sound. We show how an attacker can inject arbitrary audio signals to a target microphone by aiming an amplitude-modulated light at the…

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

Interaction with Large Language Models (LLMs) is primarily carried out via prompting. A prompt is a natural language instruction designed to elicit certain behaviour or output from a model. In theory, natural language prompts enable…

Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data, making applications like image captioning, visual question answering, and multi-modal content creation possible. This ability to…

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

Multimodal large language models (MLLMs) have become the cornerstone of today's generative AI ecosystem, sparking intense competition among tech giants and startups. In particular, an MLLM generates a text response given a prompt consisting…

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. However, the visual modules introduces new challenges in terms of robustness for…

Deep neural networks (DNNs) offer significant promise for improving breast cancer diagnosis in medical imaging. However, these models are highly susceptible to adversarial attacks--small, imperceptible changes that can mislead…

Large Language Models (LLMs) are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs…

Contextual speech recognition refers to the ability to identify preferences for specific content based on contextual information. Recently, leveraging the contextual understanding capabilities of Speech LLM to achieve contextual biasing by…

Jailbreaking large language models (LLMs) has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts to elicit…

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt…

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, notably in connecting ideas and adhering to logical rules to solve problems. These models have evolved to accommodate various data modalities, including sound…

Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts. Investigating multimodal systems' robustness via…

We present ImageBind-LLM, a multi-modality instruction tuning method of large language models (LLMs) via ImageBind. Existing works mainly focus on language and image instruction tuning, different from which, our ImageBind-LLM can respond to…

The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate \eg, the ImageNet trained model, and transferred to change the decision of an…