Related papers: Transferable Unlearnable Examples
Adversarial attacks are a type of attack on machine learning models where an attacker deliberately modifies the inputs to cause the model to make incorrect predictions. Adversarial attacks can have serious consequences, particularly in…
Machine unlearning has become a pivotal task to erase the influence of data from a trained model. It adheres to recent data regulation standards and enhances the privacy and security of machine learning applications. In this work, we…
Given an existing system learned from previous source domains, it is desirable to adapt the system to new domains without accessing and forgetting all the previous domains in some applications. This problem is known as domain expansion.…
Transfer learning is prevalent as a technique to efficiently generate new models (Student models) based on the knowledge transferred from a pre-trained model (Teacher model). However, Teacher models are often publicly available for sharing…
Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data. We argue this not only risks reinforcing exposure to sensitive data, but also fundamentally…
Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…
Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the model's learning…
This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequence models---a common type of machine-learning model. Because such…
Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…
Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulnerable to human…
Online learning has been in the spotlight from the machine learning society for a long time. To handle massive data in Big Data era, one single learner could never efficiently finish this heavy task. Hence, in this paper, we propose a novel…
In the unsupervised open set domain adaptation (UOSDA), the target domain contains unknown classes that are not observed in the source domain. Researchers in this area aim to train a classifier to accurately: 1) recognize unknown target…
While machine learning has achieved remarkable results in a wide variety of domains, the training of models often requires large datasets that may need to be collected from different individuals. As sensitive information may be contained in…
In conventional supervised learning, a training dataset is given with ground-truth labels from a known label set, and the learned model will classify unseen instances to known labels. This paper studies a new problem setting in which there…
In this paper, we study a transfer reinforcement learning problem where the state transitions and rewards are affected by the environmental context. Specifically, we consider a demonstrator agent that has access to a context-aware policy…
In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new…
We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…
Difference-in-differences (DID) is commonly used to estimate treatment effects but is infeasible in settings where data are unpoolable due to privacy concerns or legal restrictions on data sharing, particularly across jurisdictions. In this…
Recent advances in machine learning, particularly in Natural Language Processing (NLP), have produced powerful models trained on vast datasets. However, these models risk leaking sensitive information, raising privacy concerns. In response,…
Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…