相关论文: Tuning for Two Adversaries: Enhancing the Robustne…

Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model…

Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…

Transfer-based adversarial attacks raise a severe threat to real-world deep learning systems since they do not require access to target models. Adversarial training (AT), which is recognized as the strongest defense against white-box…

Evaluating the adversarial robustness of machine learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fast minimum-norm attacks by automating the selection of the…

Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on…

Adversarial training (AT) with projected gradient descent is the most popular method to improve model robustness under adversarial attacks. However, computational overheads become prohibitively large when AT is applied to large backbone…

Differentially private (DP) transfer learning, i.e., fine-tuning a pretrained model on private data, is the current state-of-the-art approach for training large models under privacy constraints. We focus on two key hyperparameters in this…

Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen…

Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot…

This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without…

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important. We propose to simultaneously tackle Performance,…

Parameter sharing has proven to be a parameter-efficient approach. Previous work on Transformers has focused on sharing parameters in different layers, which can improve the performance of models with limited parameters by increasing model…

Design of adversarial attacks for deep neural networks, as well as methods of adversarial training against them, are subject of intense research. In this paper, we propose methods to train against distributional attack threats, extending…

Adversarial training improves the robustness of neural networks against adversarial attacks, albeit at the expense of the trade-off between standard and robust generalization. To unveil the underlying factors driving this phenomenon, we…

Research on adversarial robustness is primarily focused on image and text data. Yet, many scenarios in which lack of robustness can result in serious risks, such as fraud detection, medical diagnosis, or recommender systems often do not…

Transfer learning eases the burden of training a well-performed model from scratch, especially when training data is scarce and computation power is limited. In deep learning, a typical strategy for transfer learning is to freeze the early…

Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such…

Deep neural networks are vulnerable to adversarial examples -- minor perturbations added to a model's input which cause the model to output an incorrect prediction. We introduce a new method for improving the efficacy of adversarial attacks…

Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naive formulations often degrade performance and in particular, identifying the tasks that would benefit from…