Related papers: Gradient-based Jailbreak Images for Multimodal Fus…

Along with the rapid advancement of numerous Text-to-Video (T2V) models, growing concerns have emerged regarding their safety risks. While recent studies have explored vulnerabilities in models like LLMs, VLMs, and Text-to-Image (T2I)…

Unified multimodal models have recently shown remarkable gains in both capability and versatility, yet most leading systems are still trained from scratch and require substantial computational resources. In this paper, we show that…

Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision…

Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities. However, more modalities bring more vulnerabilities to being utilized for jailbreak…

The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…

Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate…

Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we…

Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based…

Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input.…

Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as input. One major reason is the cross-image information leakage, where the model…

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol…

Gradient inversion attacks aim to reconstruct local training data from intermediate gradients exposed in the federated learning framework. Despite successful attacks, all previous methods, starting from reconstructing a single data point…

Large language models (LLMs) remain vulnerable to a slew of adversarial attacks and jailbreaking methods. One common approach employed by white-hat attackers, or red-teamers, is to process model inputs and outputs using string-level…

Although reward models have been successful in improving multimodal large language models, the reward models themselves remain brutal and contain minimal information. Notably, existing reward models only mimic human annotations by assigning…

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Multimodal text-to-image generation remains constrained by the difficulty of maintaining semantic alignment and professional-level detail across diverse visual domains. We propose a multi-agent reinforcement learning framework that…

Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in…

This paper studies the vulnerabilities of transformer-based Large Language Models (LLMs) to jailbreaking attacks, focusing specifically on the optimization-based Greedy Coordinate Gradient (GCG) strategy. We first observe a positive…

Image segmentation is an important problem in many safety-critical applications. Recent studies show that modern image segmentation models are vulnerable to adversarial perturbations, while existing attack methods mainly follow the idea of…

Large Vision-Language Models (LVLMs) with discrete image tokenizers unify multimodal representations by encoding visual inputs into a finite set of tokens. Despite their effectiveness, we find that these models still hallucinate…