Related papers: Toward Efficient Inference Attacks: Shadow Model S…
The real-world traffic networks undergo expansion through the installation of new sensors, implying that the traffic patterns continually evolve over time. Incrementally training a model on the newly added sensors would make the model…
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…
Mixture-of-Experts (MoE) is a neural network architecture that adds sparsely activated expert blocks to a base model, increasing the number of parameters without impacting computational costs. However, current distributed deep learning…
Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to…
Membership Inference Attacks (MIAs) aim to identify specific data samples within the private training dataset of machine learning models, leading to serious privacy violations and other sophisticated threats. Many practical black-box MIAs…
We study how inherent randomness in the training process -- where each sample (or client in federated learning) contributes only to a randomly selected portion of training -- can be leveraged for privacy amplification. This includes (1)…
This paper proposes Shoggoth, an efficient edge-cloud collaborative architecture, for boosting inference performance on real-time video of changing scenes. Shoggoth uses online knowledge distillation to improve the accuracy of models…
Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…
Scaling the size of a model enhances its capabilities but significantly increases computation complexity. Mixture-of-Experts models (MoE) address the issue by allowing model size to scale up without substantially increasing training or…
Deep model training on extensive datasets is increasingly becoming cost-prohibitive, prompting the widespread adoption of deep model fusion techniques to leverage knowledge from pre-existing models. From simple weight averaging to more…
This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data…
Transfer learning aims to leverage knowledge from pre-trained models to benefit the target task. Prior transfer learning work mainly transfers from a single model. However, with the emergence of deep models pre-trained from different…
We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…
Despite machine learning models being widely used today, the relationship between a model and its training dataset is not well understood. We explore correlation inference attacks, whether and when a model leaks information about the…
Mixture-of-Experts (MoE) models substantially improve performance by increasing the capacity of dense architectures. However, directly training MoE models requires considerable computational resources and introduces extra overhead in…
Recently, recommender systems have achieved promising performances and become one of the most widely used web applications. However, recommender systems are often trained on highly sensitive user data, thus potential data leakage from…
Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…
Most existing secure neural network inference protocols based on secure multi-party computation (MPC) typically support at most four participants, demonstrating severely limited scalability. Liu et al. (USENIX Security'24) presented the…
Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…
Recently, the membership inference attack poses a serious threat to the privacy of confidential training data of machine learning models. This paper proposes a novel adversarial example based privacy-preserving technique (AEPPT), which adds…