Related papers: Prediction Exposes Your Face: Black-box Model Inve…

The proliferation of text-to-image diffusion models (T2I DMs) has led to an increased presence of AI-generated images in daily life. However, biased T2I models can generate content with specific tendencies, potentially influencing people's…

Recent works have demonstrated the feasibility of inverting face recognition systems, enabling to recover convincing face images using only their embeddings. We leverage such template inversion models to develop a novel type ofdeep morphing…

In a model inversion (MI) attack, an adversary abuses access to a machine learning (ML) model to infer and reconstruct private training data. Remarkable progress has been made in the white-box and black-box setups, where the adversary has…

Model Inversion (MI) attacks aim to reconstruct private training data by abusing access to machine learning models. Contemporary MI attacks have achieved impressive attack performance, posing serious threats to privacy. Meanwhile, all…

Face recognition poses serious privacy risks due to its reliance on sensitive and immutable biometric data. While modern systems mitigate privacy risks by mapping facial images to embeddings (commonly regarded as privacy-preserving), model…

Machine learning models often pose a threat to the privacy of individuals whose data is part of the training set. Several recent attacks have been able to infer sensitive information from trained models, including model inversion or…

Deep hashing improves retrieval efficiency through compact binary codes, yet it introduces severe and often overlooked privacy risks. The ability to reconstruct original training data from hash codes could lead to serious threats such as…

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…

Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model. In this work, we study membership inference in the white-box setting in…

Increasing use of ML technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakages of sensitive…

With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered. One such vulnerability makes itpossible for an adversary to obtain private information about the types of…

Text-to-Image (T2I) models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work (NSFW) content. To investigate the…

The rapid adoption of deep learning in sensitive domains has brought tremendous benefits. However, this widespread adoption has also given rise to serious vulnerabilities, particularly model inversion (MI) attacks, posing a significant…

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing…

Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for high accessible…

Continual learning (CL) aims to incrementally train a model on a sequence of tasks while retaining performance on prior ones. However, storing and replaying data is often infeasible due to privacy or security constraints and impractical for…

Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions…

Model Inversion (MI) attacks aim to recover the private training data from the target model, which has raised security concerns about the deployment of DNNs in practice. Recent advances in generative adversarial models have rendered them…

Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning systems via the model…

Image-to-Image (I2I) translation is a heated topic in academia, and it also has been applied in real-world industry for tasks like image synthesis, super-resolution, and colorization. However, traditional I2I translation methods train data…