相关论文: Direct Unlearning Optimization for Robust and Safe…

Large language models trained on web-scale data can memorize private or sensitive knowledge, raising significant privacy risks. Although some unlearning methods mitigate these risks, they remain vulnerable to "relearning" during subsequent…

Text-guided image manipulation with diffusion models enables flexible and precise editing based on prompts, but raises ethical and copyright concerns due to potential unauthorized modifications. To address this, we propose SecureT2I, a…

Recent advancements in controllable text-to-image (T2I) diffusion models, such as Ctrl-X and FreeControl, have demonstrated robust spatial and appearance control without requiring auxiliary module training. However, these models often…

Machine unlearning in text-to-image diffusion models aims to remove targeted concepts while preserving overall utility. Prior diffusion unlearning methods typically rely on supervised weight edits or global penalties; reinforcement-learning…

Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended…

Text-to-image (T2I) personalization allows users to guide the creative image generation process by combining their own visual concepts in natural language prompts. Recently, encoder-based techniques have emerged as a new effective approach…

Text-to-image models have recently made significant advances in generating realistic and semantically coherent images, driven by advanced diffusion models and large-scale web-crawled datasets. However, these datasets often contain…

Recent advances in diffusion models have notably enhanced text-to-image (T2I) generation quality, but they also raise the risk of generating unsafe content. Traditional safety methods like text blacklisting or harmful content classification…

Text-to-image (T2I) diffusion models have revolutionized visual content creation, but extending these capabilities to text-to-video (T2V) generation remains a challenge, particularly in preserving temporal consistency. Existing methods that…

The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry. The significant advances in text-to-image generation techniques have prompted global discussions on privacy,…

As text-to-image models grow increasingly powerful and complex, their burgeoning size presents a significant obstacle to widespread adoption, especially on resource-constrained devices. This paper presents a pioneering study on…

Training a deep neural network to maximize a target objective has become the standard recipe for successful machine learning over the last decade. These networks can be optimized with supervised learning, if the target objective is…

This work studies the problem of large language model (LLM) unlearning, aiming to remove unwanted data influences (e.g., copyrighted or harmful content) while preserving model utility. Despite the increasing demand for unlearning, a…

State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Consequently, Content Removal Techniques (CRTs) have emerged as a…

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…

Training AI models to understand images without costly labeled data remains a challenge. We combine two techniques--DINO (teacher-student learning) and Barlow Twins (redundancy reduction)--to create a model that learns better with fewer…

Instruction-based image editing has achieved remarkable progress; however, models solely trained via supervised fine-tuning often overfit to annotated patterns, hindering their ability to explore and generalize beyond training…

State-of-the-art Diffusion Models (DMs) produce highly realistic images. While prior work has successfully mitigated Not Safe For Work (NSFW) content in the visual domain, we identify a novel threat: the generation of NSFW text embedded…

In autonomous driving, vision-centric 3D object detection recognizes and localizes 3D objects from RGB images. However, due to high annotation costs and diverse outdoor scenes, training data often fails to cover all possible test scenarios,…

Large language models (LLMs) exhibit powerful capabilities but risk memorizing sensitive personally identifiable information (PII) from their training data, posing significant privacy concerns. While machine unlearning techniques aim to…