Related papers: Low Resource Reconstruction Attacks Through Benign…

Document understanding models are increasingly employed by companies to supplant humans in processing sensitive documents, such as invoices, tax notices, or even ID cards. However, the robustness of such models to privacy attacks remains…

With the rapid advancement of generative AI, users increasingly rely on image-generation models for image design and creation. To achieve faithful outputs, users typically engage in multi-turn interactions during image refinement: a…

We study what provable privacy attacks can be shown on trained, 2-layer ReLU neural networks. We explore two types of attacks; data reconstruction attacks, and membership inference attacks. We prove that theoretical results on the implicit…

Advances in brain decoding, particularly visual image reconstruction, have sparked discussions about the societal implications and ethical considerations of neurotechnology. As these methods aim to recover visual experiences from brain…

DeepFake is becoming a real risk to society and brings potential threats to both individual privacy and political security due to the DeepFaked multimedia are realistic and convincing. However, the popular DeepFake passive detection is an…

Recent text-to-image diffusion models have shown surprising performance in generating high-quality images. However, concerns have arisen regarding the unauthorized data usage during the training or fine-tuning process. One example is when a…

Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set images has sparked concerns about the originality of the…

Generative models can reconstruct face images from encoded representations (templates) bearing remarkable likeness to the original face, raising security and privacy concerns. We present \textsc{FaceCloak}, a neural network framework that…

Denoising probabilistic diffusion models have shown breakthrough performance to generate more photo-realistic images or human-level illustrations than the prior models such as GANs. This high image-generation capability has stimulated the…

The increasing reliance on large language models (LLMs) such as ChatGPT in various fields emphasizes the importance of ``prompt engineering,'' a technology to improve the quality of model outputs. With companies investing significantly in…

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…

Removing personally identifiable information (PII) from texts is necessary to comply with various data protection regulations and to enable data sharing without compromising privacy. However, recent works show that documents sanitized by…

Recent approaches to jointly reconstruct 3D humans and objects from a single RGB image represent 3D shapes with template-based or coarse models, which fail to capture details of loose clothing on human bodies. In this paper, we introduce a…

Machine unlearning aims to remove specific outputs from trained models, often at the concept level, such as forgetting all occurrences of a particular celebrity or filtering content via text prompts. However, many undesired outputs, such as…

Due to the subtleness, implicity, and different possible interpretations perceived by different people, detecting undesirable content from text is a nuanced difficulty. It is a long-known risk that language models (LMs), once trained on…

Model stealing poses a significant security risk in machine learning by enabling attackers to replicate a black-box model without access to its training data, thus jeopardizing intellectual property and exposing sensitive information.…

Despite excellent average-case performance of many image classifiers, their performance can substantially deteriorate on semantically coherent subgroups of the data that were under-represented in the training data. These systematic errors…

Diffusion models pose risks of privacy breaches and copyright disputes, primarily stemming from the potential utilization of unauthorized data during the training phase. The Training Membership Inference (TMI) task aims to determine whether…

The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied, prompt-based…

Generative models have demonstrated revolutionary success in various visual creation tasks, but in the meantime, they have been exposed to the threat of leaking private information of their training data. Several membership inference…