相关论文: JANUS: A Lightweight Framework for Jailbreaking Te…

Despite the impressive generative capabilities of text-to-image (T2I) diffusion models, they remain vulnerable to generating inappropriate content, especially when confronted with implicit sexual prompts. Unlike explicit harmful prompts,…

Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbreak methods face significant drawbacks. Token-level jailbreak attacks often produce incoherent or…

Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known as jailbreaks. Unlike traditional adversarial examples…

Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of…

Text-to-image (T2I) generation with Stable Diffusion models (SDMs) involves high computing demands due to billion-scale parameters. To enhance efficiency, recent studies have reduced sampling steps and applied network quantization while…

Diffusion models have emerged as a dominant paradigm for generative modeling across a wide range of domains, including prompt-conditional generation. The vast majority of samplers, however, rely on forward discretization of the reverse…

Text-to-Image (T2I) models have made significant advancements in recent years, but they still struggle to accurately capture intricate details specified in complex compositional prompts. While fine-tuning T2I models with reward objectives…

Text-to-image (T2I) models have advanced creative content generation, yet their reliance on large uncurated datasets often reproduces societal biases. We present FairT2I, a training-free and interactive framework grounded in a…

Based on recent advanced diffusion models, Text-to-image (T2I) generation models have demonstrated their capabilities to generate diverse and high-quality images. However, leveraging their potential for real-world content creation,…

Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, particularly generating not-safe-for-work (NSFW) content, such…

Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for high accessible…

High-stakes synthetic data generation faces a fundamental Quadrilemma: achieving Fidelity to the original distribution, Control over complex logical constraints, Reliability in uncertainty estimation, and Efficiency in computational cost --…

The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a skewed worldview and restrict opportunities for minority groups. In…

As Large Language Models (LLMs) become ubiquitous, the challenge of securing them against adversarial "jailbreaking" attacks has intensified. Current defense strategies often rely on computationally expensive external classifiers or brittle…

Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generation as a black box, returning only terminal toxicity scores…

Text-to-image diffusion models often memorize training data, revealing a fundamental failure to generalize beyond the training set. Current mitigation strategies typically sacrifice image quality or prompt alignment to reduce memorization.…

Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness but, more critically, by its stealthiness. However, existing…

As recent advances in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications have emerged. Despite the impressive results achieved by…

As text-to-image (T2I) synthesis models increase in size, they demand higher inference costs due to the need for more expensive GPUs with larger memory, which makes it challenging to reproduce these models in addition to the restricted…

Text-to-image diffusion models, such as Stable Diffusion, have shown exceptional potential in generating high-quality images. However, recent studies highlight concerns over the use of unauthorized data in training these models, which may…