相关论文: Knowledge Distillation-Based Model Extraction Atta…

With the rapid development of artificial intelligence (AI), especially in the medical field, the need for its explainability has grown. In medical image analysis, a high degree of transparency and model interpretability can help clinicians…

Machine Learning as a Service (MLaaS) has emerged as a widely adopted paradigm for providing access to deep neural network (DNN) models, enabling users to conveniently leverage these models through standardized APIs. However, such services…

Model distillation is frequently proposed as a technique to reduce the privacy leakage of machine learning. These empirical privacy defenses rely on the intuition that distilled ``student'' models protect the privacy of training data, as…

The growing popularity of Machine Learning (ML) has led to its deployment in various sensitive domains, which has resulted in significant research focused on ML security and privacy. However, in some applications, such as Augmented/Virtual…

Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction…

Machine Learning (ML) has emerged as a core technology to provide learning models to perform complex tasks. Boosted by Machine Learning as a Service (MLaaS), the number of applications relying on ML capabilities is ever increasing. However,…

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

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…

Membership inference attacks are a key measure to evaluate privacy leakage in machine learning (ML) models. These attacks aim to distinguish training members from non-members by exploiting differential behavior of the models on member and…

While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, Machine Learning as a Service (MLaaS) has emerged,…

Image-to-image translation models are shown to be vulnerable to the Membership Inference Attack (MIA), in which the adversary's goal is to identify whether a sample is used to train the model or not. With daily increasing applications based…

Modern network intrusion detection systems (NIDS) frequently utilize the predictive power of complex deep learning models. However, the "black-box" nature of such deep learning methods adds a layer of opaqueness that hinders the proper…

We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP-based ML implementations are so loose that they do not…

As a solution concept in cooperative game theory, Shapley value is highly recognized in model interpretability studies and widely adopted by the leading Machine Learning as a Service (MLaaS) providers, such as Google, Microsoft, and IBM.…

Training a machine learning model with data following a meaningful order, i.e., from easy to hard, has been proven to be effective in accelerating the training process and achieving better model performance. The key enabling technique is…

Training machine learning models on privacy-sensitive data has become a popular practice, driving innovation in ever-expanding fields. This has opened the door to new attacks that can have serious privacy implications. One such attack, the…

Machine Learning-as-a-Service (MLaaS) has become a widespread paradigm, making even the most complex machine learning models available for clients via e.g. a pay-per-query principle. This allows users to avoid time-consuming processes of…

With the rising need of interpretable machine learning methods, there is a necessity for a rise in human effort to provide diverse explanations of the influencing factors of the model decisions. To improve the trust and transparency of…

Explainable Artificial Intelligence (XAI) aims to uncover the decision-making processes of AI models. However, the data used for such explanations can pose security and privacy risks. Existing literature identifies attacks on machine…

The use of machine learning (ML) has become increasingly prevalent in various domains, highlighting the importance of understanding and ensuring its safety. One pressing concern is the vulnerability of ML applications to model stealing…