相关论文: Jailbreaking Prompt Attack: A Controllable Adversa…

The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual…

The fine-tuning technique for text-to-image diffusion models facilitates image customization but risks privacy breaches and opinion manipulation. Current research focuses on prompt- or image-level adversarial attacks for anti-customization,…

As Large Language Models (LLMs) are increasingly being deployed in safety-critical applications, their vulnerability to potential jailbreaks -- malicious prompts that can disable the safety mechanism of LLMs -- has attracted growing…

Text-to-image models are vulnerable to the stepwise "Divide-and-Conquer Attack" (DACA) that utilize a large language model to obfuscate inappropriate content in prompts by wrapping sensitive text in a benign narrative. To mitigate stepwise…

Jailbreak attacks against multimodal large language Models (MLLMs) are a significant research focus. Current research predominantly focuses on maximizing attack success rate (ASR), often overlooking whether the generated responses actually…

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…

Safety is critical to the usage of large language models (LLMs). Multiple techniques such as data filtering and supervised fine-tuning have been developed to strengthen LLM safety. However, currently known techniques presume that corpora…

Text-to-image (T2I) generative models have gained increased popularity in the public domain. While boasting impressive user-guided generative abilities, their black-box nature exposes users to intentionally- and intrinsically-biased…

Recent advances in text-to-image generative models have raised concerns about their potential to produce harmful content when provided with malicious input text prompts. To address this issue, two main approaches have emerged: (1)…

Multimodal Large Language Models (MLLMs) have showcased impressive performance in a variety of multimodal tasks. On the other hand, the integration of additional image modality may allow the malicious users to inject harmful content inside…

While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-trained text encoders…

Large Language Models (LLMs) can be used to red team other models (e.g. jailbreaking) to elicit harmful contents. While prior works commonly employ open-weight models or private uncensored models for doing jailbreaking, as the…

Large language models (LLMs), such as ChatGPT, have emerged with astonishing capabilities approaching artificial general intelligence. While providing convenience for various societal needs, LLMs have also lowered the cost of generating…

Image-to-Video (I2V) generation models, which condition video generation on reference images, have shown emerging visual instruction-following capability, allowing certain visual cues in reference images to act as implicit control signals…

Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be…

Diffusion models (DMs) have revolutionized data generation, particularly in text-to-image (T2I) synthesis. However, the widespread use of personalized generative models raises significant concerns regarding privacy violations and copyright…

We propose Instruct2Attack (I2A), a language-guided semantic attack that generates semantically meaningful perturbations according to free-form language instructions. We make use of state-of-the-art latent diffusion models, where we…

Jailbreaking techniques trick Large Language Models (LLMs) into producing restricted output, posing a potential threat. One line of defense is to use another LLM as a Judge to evaluate the harmfulness of generated text. However, we reveal…

State-of-the-art Text-to-Image models like Stable Diffusion and DALLE$\cdot$2 are revolutionizing how people generate visual content. At the same time, society has serious concerns about how adversaries can exploit such models to generate…

Recent advancements in Text-to-Image (T2I) diffusion models have demonstrated impressive success in generating high-quality images with zero-shot generalization capabilities. Yet, current models struggle to closely adhere to prompt…