Related papers: Can't Hide Behind the API: Stealing Black-Box Comm…
Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…
Recent advances in artificial intelligence research have led to a profusion of studies that apply deep learning to problems in image analysis and natural language processing among others. Additionally, the availability of open-source…
Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…
Vector Database (VDB) can efficiently index and search high-dimensional vector embeddings from unstructured data, crucially enabling fast semantic similarity search essential for modern AI applications like generative AI and recommendation…
This study investigates the privacy risks associated with text embeddings, focusing on the scenario where attackers cannot access the original embedding model. Contrary to previous research requiring direct model access, we explore a more…
Complex deep learning models now achieve state of the art performance for many document retrieval tasks. The best models process the query or claim jointly with the document. However for fast scalable search it is desirable to have document…
Despite the broad application of Machine Learning models as a Service (MLaaS), they are vulnerable to model stealing attacks. These attacks can replicate the model functionality by using the black-box query process without any prior…
AI models and services are used in a growing number of highstakes areas, resulting in a need for increased transparency. Consistent with this, several proposals for higher quality and more consistent documentation of AI data, models, and…
The rapid advancement of deep learning has turned models into highly valuable assets due to their reliance on massive data and costly training processes. However, these models are increasingly vulnerable to leakage and theft, highlighting…
How much private information do text embeddings reveal about the original text? We investigate the problem of embedding \textit{inversion}, reconstructing the full text represented in dense text embeddings. We frame the problem as…
Machine learning as a Service (MLaaS) allows users to query the machine learning model in an API manner, which provides an opportunity for users to enjoy the benefits brought by the high-performance model trained on valuable data. This…
With the development of computational power and techniques for data collection, deep learning demonstrates a superior performance over most existing algorithms on visual benchmark data sets. Many efforts have been devoted to studying the…
Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…
Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator…
Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems. It inevitably requires a prohibitively large amount of computational cost and even entails the downtime of the service.…
Today's success of state of the art methods for semantic segmentation is driven by large datasets. Data is considered an important asset that needs to be protected, as the collection and annotation of such datasets comes at significant…
A pseudo independent (PI) model is a probabilistic domain model (PDM) where proper subsets of a set of collectively dependent variables display marginal independence. PI models cannot be learned correctly by many algorithms that rely on a…
Recent advancements in Artificial Intelligence namely in Deep Learning has heightened its adoption in many applications. Some are playing important roles to the extent that we are heavily dependent on them for our livelihood. However, as…
Deep Learning has recently become hugely popular in machine learning, providing significant improvements in classification accuracy in the presence of highly-structured and large databases. Researchers have also considered privacy…
Artificial intelligence (AI) applications in healthcare and medicine have increased in recent years. To enable access to personal data, Trusted Research environments (TREs) provide safe and secure environments in which researchers can…