相关论文: Gradient-based Jailbreak Images for Multimodal Fus…

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and concept removal techniques have been introduced to block…

Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks. We revisit this…

The systems and software powered by Large Language Models (LLMs) and Multi-Modal LLMs (MLLMs) have played a critical role in numerous scenarios. However, current LLM systems are vulnerable to prompt-based attacks, with jailbreaking attacks…

Despite the remarkable generation capabilities of diffusion models, recent studies have shown that they can memorize and create harmful content when given specific text prompts. Although fine-tuning approaches have been developed to…

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Various (text) prompt filters and (image) safety checkers have been implemented to mitigate the misuse of Text-to-Image (T2I) models in creating Not-Safe-For-Work (NSFW) content. In order to expose potential security vulnerabilities of such…

As a cornerstone in language modeling, tokenization involves segmenting text inputs into pre-defined atomic units. Conventional statistical tokenizers often disrupt constituent boundaries within words, thereby corrupting semantic…

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer…

Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we introduce a multi-image setting for studying typographic…

Optimization-based jailbreaks typically adopt the Toxic-Continuation setting in large vision-language models (LVLMs), following the standard next-token prediction objective. In this setting, an adversarial image is optimized to make the…

Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the…

In language processing, transformers benefit greatly from text being condensed. This is achieved through a larger vocabulary that captures word fragments instead of plain characters. This is often done with Byte Pair Encoding. In the…

In this paper, we study the harmlessness alignment problem of multimodal large language models (MLLMs). We conduct a systematic empirical analysis of the harmlessness performance of representative MLLMs and reveal that the image input poses…

Natural Language Processing (NLP) models are used for text-related tasks such as classification and generation. To complete these tasks, input data is first tokenized from human-readable text into a format the model can understand, enabling…

In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details,…

While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce…

Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of training automated multi-turn attackers to probe model safety…

Jailbreak attacks on large language models (LLMs) involve inducing these models to generate harmful content that violates ethics or laws, posing a significant threat to LLM security. Current jailbreak attacks face two main challenges: low…

In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks predominantly focus on the visual modality, perturbing solely…