Related papers: PID: Prompt-Independent Data Protection Against La…

Diffusion models have attracted significant attention due to its exceptional data generation capabilities in fields such as image synthesis. However, recent studies have shown that diffusion models are vulnerable to copyright infringement…

Proactive defense methods protect portrait images from unauthorized editing or talking face generation (TFG) by introducing pixel-level protective perturbations, and have already attracted increasing attention for privacy protection. In…

Large Language Models (LLMs) hold promise for advancing legal practice by automating complex tasks and improving access to justice. However, their adoption is limited by concerns over client confidentiality, especially when lawyers include…

Federated Learning (FL) facilitates collaborative model training while preserving data locality; however, the exchange of gradients renders the system vulnerable to Gradient Inversion Attacks (GIAs), allowing adversaries to reconstruct…

Diffusion Transformers (DiTs) have recently achieved remarkable success in text-guided image generation. In image editing, DiTs project text and image inputs to a joint latent space, from which they decode and synthesize new images.…

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,…

Recent advancements in diffusion models have made fine-tuning text-to-image models for personalization increasingly accessible, but have also raised significant concerns regarding unauthorized data usage and privacy infringement. Current…

The increasingly pervasive facial recognition (FR) systems raise serious concerns about personal privacy, especially for billions of users who have publicly shared their photos on social media. Several attempts have been made to protect…

The rapid proliferation of speech-enabled technologies, including virtual assistants, video conferencing platforms, and wearable devices, has raised significant privacy concerns, particularly regarding the inference of sensitive emotional…

Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box…

Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple instructions to extract data, both of which well-alignment…

Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…

Privacy policies are often obfuscated by their complexity, which impedes transparency and informed consent. Conventional machine learning approaches for automatically analyzing these policies demand significant resources and substantial…

Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this…

Image manipulation under the guidance of textual descriptions has recently received a broad range of attention. In this study, we focus on the regional editing of images with the guidance of given text prompts. Different from current…

Most practical high-resolution text-to-image systems, including latent diffusion and autoregressive models, perform generation in a compact latent space, and a decoder maps the generated latents back to pixels. Yet the latent-to-pixel…

With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the integration of additional modalities, MLLMs are exposed to…

In LLM/VLM agents, prompt privacy risk propagates beyond a single model call because raw user content can flow into retrieval queries, memory writes, tool calls, and logs. Existing de-identification pipelines address document boundaries but…

Retrieval-Augmented Generation (RAG) and Supervised Finetuning (SFT) have become the predominant paradigms for equipping Large Language Models (LLMs) with external knowledge for diverse, knowledge-intensive tasks. However, while such…

System prompts that include detailed instructions to describe the task performed by the underlying LLM can easily transform foundation models into tools and services with minimal overhead. They are often considered intellectual property,…