Related papers: On the Adversarial Robustness of Multi-Modal Found…

Rising usage of deep neural networks to perform decision making in critical applications like medical diagnosis and financial analysis have raised concerns regarding their reliability and trustworthiness. As automated systems become more…

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…

Despite the remarkable performance of video-based large language models (LLMs), their adversarial threat remains unexplored. To fill this gap, we propose the first adversarial attack tailored for video-based LLMs by crafting flow-based…

Recently, large language models (LLMs) have taken the spotlight in natural language processing. Further, integrating LLMs with vision enables the users to explore more emergent abilities in multimodality. Visual language models (VLMs), such…

This paper examines the dual-use challenges of foundation models and the consequent risks they pose for international security. As artificial intelligence (AI) models are increasingly tested and deployed across both civilian and military…

Recent advances in instruction-following large language models (LLMs) have led to dramatic improvements in a range of NLP tasks. Unfortunately, we find that the same improved capabilities amplify the dual-use risks for malicious purposes of…

Modern image-to-text systems typically adopt the encoder-decoder framework, which comprises two main components: an image encoder, responsible for extracting image features, and a transformer-based decoder, used for generating captions.…

Large language and vision-language models are rapidly being deployed in practice thanks to their impressive capabilities in instruction following, in-context learning, and so on. This raises an urgent need to carefully analyse their…

As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this…

Multimodal hateful content detection is a challenging task that requires complex reasoning across visual and textual modalities. Therefore, creating a meaningful multimodal representation that effectively captures the interplay between…

Multimodal Large Language Models (MLLMs) that integrate text and other modalities (especially vision) have achieved unprecedented performance in various multimodal tasks. However, due to the unsolved adversarial robustness problem of vision…

The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security risks, including…

NLP models today strive for supporting multiple languages and modalities, improving accessibility for diverse users. In this paper, we evaluate their multilingual, multimodal capabilities by testing on a visual reasoning task. We observe…

Recently, Large Multi-modal Models (LMMs) have demonstrated their ability to understand the visual contents of images given the instructions regarding the images. Built upon the Large Language Models (LLMs), LMMs also inherit their…

As large language models become integral to high-stakes applications, ensuring their robustness and fairness is critical. Despite their success, large language models remain vulnerable to adversarial attacks, where small perturbations, such…

Foundation models (FMs) for computer vision learn rich and robust representations, enabling their adaptation to task/domain-specific deployments with little to no fine-tuning. However, we posit that the very same strength can make…

Utilizing a shared embedding space, emerging multimodal models exhibit unprecedented zero-shot capabilities. However, the shared embedding space could lead to new vulnerabilities if different modalities can be misaligned. In this paper, we…

We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterparts but believe them to be false. Exploiting this…

In spite of the successful application in many fields, machine learning models today suffer from notorious problems like vulnerability to adversarial examples. Beyond falling into the cat-and-mouse game between adversarial attack and…

Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…