Related papers: Membership Inference Attacks Against Text-to-image…

As large-scale models such as Large Language Models (LLMs) and Large Multimodal Models (LMMs) see increasing deployment, their privacy risks remain underexplored. Membership Inference Attacks (MIAs), which reveal whether a data point was…

Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task.…

The rise of generative image models leads to privacy concerns when it comes to the huge datasets used to train such models. This paper investigates the possibility of inferring if a set of face images was used for fine-tuning a Latent…

While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-trained text encoders…

Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data…

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

A surprising phenomenon in modern machine learning is the ability of a highly overparameterized model to generalize well (small error on the test data) even when it is trained to memorize the training data (zero error on the training data).…

Modern text-to-image (T2I) generation systems (e.g., DALL$\cdot$E 3) exploit the memory mechanism, which captures key information in multi-turn interactions for faithful generation. Despite its practicality, the security analyses of this…

The usage of deep learning is being escalated in many applications. Due to its outstanding performance, it is being used in a variety of security and privacy-sensitive areas in addition to conventional applications. One of the key aspects…

Training computer-vision related algorithms on medical images for disease diagnosis or image segmentation is difficult in large part due to privacy concerns. For this reason, generative image models are highly sought after to facilitate…

Membership inference attacks allow a malicious entity to predict whether a sample is used during training of a victim model or not. State-of-the-art membership inference attacks have shown to achieve good accuracy which poses a great…

Generative artificial intelligence (AI) is a widely popular technology that will have a profound impact on society and individuals. Less than a decade ago, it was thought that creative work would be among the last to be automated - yet…

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used…

Generative AI leaderboards are central to evaluating model capabilities, but remain vulnerable to manipulation. Among key adversarial objectives is rank manipulation, where an attacker must first deanonymize the models behind displayed…

Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…

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…

Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While…

Generative models are subject to overfitting and thus may potentially leak sensitive information from the training data. In this work. we investigate the privacy risks that can potentially arise from the use of generative adversarial…

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…