Related papers: Beyond Memorization: Selective Learning for Copyri…

Due to their capacity to generate novel and high-quality samples, diffusion models have attracted significant research interest in recent years. Notably, the typical training objective of diffusion models, i.e., denoising score matching,…

Generative image models, since introduction, have become a global phenomenon. From new arts becoming possible to new vectors of abuse, many new capabilities have become available. One of the challenging issues with generative models is…

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…

Recent research has seen significant interest in methods for concept removal and targeted forgetting in text-to-image diffusion models. In this paper, we conduct a comprehensive white-box analysis showing the vulnerabilities in existing…

As generative artificial intelligence technologies like Stable Diffusion advance, visual content becomes more vulnerable to misuse, raising concerns about copyright infringement. Visual watermarks serve as effective protection mechanisms,…

Despite their great success, deep neural networks rely on high-dimensional, non-robust representations, making them vulnerable to imperceptible perturbations, even in transfer scenarios. To address this, both training-time defenses (e.g.,…

An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical…

Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented methods…

Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. Robustness means the model fine-tuned by concept erasure methods resists reactivation of erased…

Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…

The training phase of deep neural networks requires substantial resources and as such is often performed on cloud servers. However, this raises privacy concerns when the training dataset contains sensitive content, e.g., facial or medical…

Deployed text-to-image diffusion models increasingly require post-hoc concept unlearning for copyright claims, artist opt-outs, safety updates, and protected-content mitigation without full retraining. A central challenge is erase-retain…

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model…

We present a practical method for protecting data during the inference phase of deep learning based on bipartite topology threat modeling and an interactive adversarial deep network construction. We term this approach \emph{Privacy…

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of…

Machine unlearning is a prominent and challenging field, driven by regulatory demands for user data deletion and heightened privacy awareness. Existing approaches involve retraining model or multiple finetuning steps for each deletion…

Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this paper, we propose a…

While many deep learning models trained on private datasets have been deployed in various practical tasks, they may pose a privacy leakage risk as attackers could recover informative data or label knowledge from models. In this work, we…

Distributed machine learning has been widely studied in order to handle exploding amount of data. In this paper, we study an important yet less visited distributed learning problem where features are inherently distributed or vertically…

This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequence models---a common type of machine-learning model. Because such…