Related papers: Attacks on Approximate Caches in Text-to-Image Dif…

Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce…

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt…

With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details requires proper prompts, and it is often unclear how a model…

Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples and achieve state-of-the-art robustness. Recent studies show that even advanced attacks cannot break such defenses…

Large language models (LLMs) possess extensive knowledge and question-answering capabilities, having been widely deployed in privacy-sensitive domains like finance and medical consultation. During LLM inferences, cache-sharing methods are…

Text-to-image generation has witnessed great progress, especially with the recent advancements in diffusion models. Since texts cannot provide detailed conditions like object appearance, reference images are usually leveraged for the…

This paper presents Packet Chasing, an attack on the network that does not require access to the network, and works regardless of the privilege level of the process receiving the packets. A spy process can easily probe and discover the…

Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…

Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make incremental updates to existing models. These updates often…

Text-to-image generation employing diffusion models has attained significant popularity due to its capability to produce high-quality images that adhere to textual prompts. However, the integration of diffusion models faces critical…

Text-to-image diffusion models, such as Stable Diffusion, generate highly realistic images from text descriptions. However, the generation of certain content at such high quality raises concerns. A prominent issue is the accurate depiction…

In-context diffusion models allow users to modify images with remarkable ease and realism. However, the same power raises serious privacy concerns: personal images can be easily manipulated for identity impersonation, misinformation, or…

Diffusion models have achieved remarkable progress in both image generation and editing. However, recent studies have revealed their vulnerability to backdoor attacks, in which specific patterns embedded in the input can manipulate the…

Diffusion models have achieved impressive results in generating high-quality images. Yet, they often struggle to faithfully align the generated images with the input prompts. This limitation is associated with synchronous denoising, where…

Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering…

Diffusion models have been remarkably successful in data synthesis. However, when these models are applied to sensitive datasets, such as banking and human face data, they might bring up severe privacy concerns. This work systematically…

Caches are used to reduce the speed differential between the CPU and memory to improve the performance of modern processors. However, attackers can use contention-based cache timing attacks to steal sensitive information from victim…

Recently, there have been significant improvements in the quality and performance of text-to-image generation, largely due to the impressive results attained by diffusion models. However, text-to-image diffusion models sometimes struggle to…

Diffusion models have emerged as state-of-the-art generative frameworks, excelling in producing high-quality multi-modal samples. However, recent studies have revealed their vulnerability to backdoor attacks, where backdoored models…