相关论文: Abusing Images and Sounds for Indirect Instruction…
Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly…
Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions…
We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "meta-instructions" that control how models answer users'…
Large Language Models (LLMs) are being enhanced with the ability to use tools and to process multiple modalities. These new capabilities bring new benefits and also new security risks. In this work, we show that an attacker can use visual…
Existing attacks against multimodal language models (MLLMs) primarily communicate instructions through text accompanied by adversarial images. In contrast, we exploit the capabilities of MLLMs to interpret non-textual instructions,…
Large Language Models (LLMs) are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of…
Large Language Models (LLMs), while powerful, are built and trained to process a single text input. In common applications, multiple inputs can be processed by concatenating them together into a single stream of text. However, the LLM is…
In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts. Despite its promising performance, crafted…
Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we investigate the potential for hidden…
Large vision-language models (LVLMs) have demonstrated their incredible capability in image understanding and response generation. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we…
Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e.g., via byte…
We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…
Multi-modal large language models (MLLMs) have emerged as powerful tools for analyzing Internet-scale image data, offering significant benefits but also raising critical safety and societal concerns. In particular, open-weight MLLMs may be…
Vision-language models (VLMs) have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks…
Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications such as robotics and situated conversational agents. When MLLMs reason over…
Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…
Vision-Language Models (VLMs) often suffer from hallucination, partly due to challenges in aligning multimodal information. We propose Prompt-in-Image, a simple method that embeds textual instructions directly into images. This removes the…
We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries and even multiple models. By backpropagating through the…
Large language models (LLMs) trained purely on text ostensibly lack any direct perceptual experience, yet their internal representations are implicitly shaped by multimodal regularities encoded in language. We test the hypothesis that…
We present PandaGPT, an approach to emPower large lANguage moDels with visual and Auditory instruction-following capabilities. Our pilot experiments show that PandaGPT can perform complex tasks such as detailed image description generation,…