相关论文: REaaS: Enabling Adversarially Robust Downstream Cl…

Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been explored for a single…

Classification-as-a-Service (CaaS) is widely deployed today in machine intelligence stacks for a vastly diverse set of applications including anything from medical prognosis to computer vision tasks to natural language processing to…

Machine learning as a service (MLaaS), and algorithm marketplaces are on a rise. Data holders can easily train complex models on their data using third party provided learning codes. Training accurate ML models requires massive labeled data…

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the…

Self-supervised learning (SSL), a paradigm harnessing unlabeled datasets to train robust encoders, has recently witnessed substantial success. These encoders serve as pivotal feature extractors for downstream tasks, demanding significant…

Pre-trained encoders are general-purpose feature extractors that can be used for many downstream tasks. Recent progress in self-supervised learning can pre-train highly effective encoders using a large volume of unlabeled data, leading to…

Predictive machine learning models nowadays are often updated in a stateless and expensive way. The two main future trends for companies that want to build machine learning-based applications and systems are real-time inference and…

Deep learning driven by large neural network models is overtaking traditional machine learning methods for understanding unstructured and perceptual data domains such as speech, text, and vision. At the same time, the "as-a-Service"-based…

The conspicuous lack of cloud-specific security certifications, in addition to the existing market fragmentation, hinder transparency and accountability in the provision and usage of European cloud services. Both issues ultimately reflect…

Deep-learning-as-a-service is a novel and promising computing paradigm aiming at providing machine/deep learning solutions and mechanisms through Cloud-based computing infrastructures. Thanks to its ability to remotely execute and train…

As a self-supervised learning paradigm, contrastive learning has been widely used to pre-train a powerful encoder as an effective feature extractor for various downstream tasks. This process requires numerous unlabeled training data and…

Classifiers in supervised learning have various security and privacy issues, e.g., 1) data poisoning attacks, backdoor attacks, and adversarial examples on the security side as well as 2) inference attacks and the right to be forgotten for…

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…

Self-supervised learning in computer vision aims to pre-train an image encoder using a large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can then be used as a feature extractor to build downstream…

Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns. Despite effectiveness, their robustness against adversarial…

With the rise of powerful foundation models, a pre-training-fine-tuning paradigm becomes increasingly popular these days: A foundation model is pre-trained using a huge amount of data from various sources, and then the downstream users only…

Reliable and trustworthy evaluation of algorithms is a challenging process. Firstly, each algorithm has its strengths and weaknesses, and the selection of test instances can significantly influence the assessment process. Secondly, the…

The simplest and often most effective way of parallelizing the training of complex machine learning models is to execute several training instances on multiple machines, scanning the hyperparameter space to optimize the underlying…

Recently, major AI providers such as Google and OpenAI have introduced Finetuning-as-a-Service (FaaS), which allows users to customize Large Language Models (LLMs) using their own data. However, this service is vulnerable to safety…

Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural network based detectors. Prior work mainly focus on crafting adversarial examples (AEs)…