相关论文: Revisiting adversarial training for the worst-perf…

Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial…

We propose a new ensemble method for detecting and classifying adversarial examples generated by state-of-the-art attacks, including DeepFool and C&W. Our method works by training the members of an ensemble to have low classification error…

Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement learning methods face challenges in striking the right…

Despite the rapid progress of neural networks, they remain highly vulnerable to adversarial examples, for which adversarial training (AT) is currently the most effective defense. While AT has been extensively studied, its practical…

Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for loss function learning have shown promising results, often…

Federated learning enables model training over a distributed corpus of agent data. However, the trained model is vulnerable to adversarial examples, designed to elicit misclassification. We study the feasibility of using adversarial…

In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally. However, recent work shows that client's private information…

Federated learning has been extensively studied and is the prevalent method for privacy-preserving distributed learning in edge devices. Correspondingly, continual learning is an emerging field targeted towards learning multiple tasks…

A commonly used learning rule is to approximately minimize the \emph{average} loss over the training set. Other learning algorithms, such as AdaBoost and hard-SVM, aim at minimizing the \emph{maximal} loss over the training set. The average…

Distributed learning is central for large-scale training of deep-learning models. However, they are exposed to a security threat in which Byzantine participants can interrupt or control the learning process. Previous attack models and their…

In online learning, the data is provided in a sequential order, and the goal of the learner is to make online decisions to minimize overall regrets. This note is concerned with continuous-time models and algorithms for several online…

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…

Malicious clients can attack federated learning systems using malicious data, including backdoor samples, during the training phase. The compromised global model will perform well on the validation dataset designed for the task, but a small…

As deep learning models are increasingly deployed in high-risk applications, robust defenses against adversarial attacks and reliable performance guarantees become paramount. Moreover, accuracy alone does not provide sufficient assurance or…

We consider an online two-stage stochastic optimization with long-term constraints over a finite horizon of $T$ periods. At each period, we take the first-stage action, observe a model parameter realization and then take the second-stage…

Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization ($i.e.,$ implicit update) is known to be beneficial to the numerical stability and structure of solution. In this…

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study…

Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logits from one clean model to guide learning of another one…

Despite strong performance in numerous applications, the fragility of deep learning to input perturbations has raised serious questions about its use in safety-critical domains. While adversarial training can mitigate this issue in…

Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real…