Related papers: Learning Better Certified Models from Empirically-…
Adversarial training is a widely adopted strategy to bolster the robustness of neural network models against adversarial attacks. This paper revisits the fundamental assumptions underlying image classification and suggests that representing…
Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…
Deep Neural Networks are being extensively used in communication systems and Automatic Modulation Classification (AMC) in particular. However, they are very susceptible to small adversarial perturbations that are carefully crafted to change…
It has been demonstrated that deep neural networks are prone to noisy examples particular adversarial samples during inference process. The gap between robust deep learning systems in real world applications and vulnerable neural networks…
Current LLM unlearning methods are not robust. A few steps of finetuning can revert their effects. We begin by showing that this is true even for an idealized form of unlearning: training to imitate a model that was never trained on…
Neural networks can learn spurious correlations in the data, often leading to performance degradation for underrepresented subgroups. Studies have demonstrated that the disparity is amplified when knowledge is distilled from a complex…
Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers). As empirically there exists a strong correlation between the performance of teacher and student…
Deep Neural Networks (DNNs) have significantly advanced the field of computer vision. To improve DNN training process, knowledge distillation methods demonstrate their effectiveness in accelerating network training by introducing a fixed…
Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences. Although certified…
Knowledge distillation is a common technique for improving the performance of a shallow student network by transferring information from a teacher network, which in general, is comparatively large and deep. These teacher networks are…
Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness uncontrolled. Recent robust DD methods improve robustness,…
Adversarial distillation in the standard min-max adversarial training framework aims to transfer adversarial robustness from a large, robust teacher network to a compact student. However, existing work often neglects to incorporate…
The vulnerability of artificial neural networks to adversarial perturbations in the black-box setting is widely studied in the literature. The majority of attack methods to construct these perturbations suffer from an impractically large…
In real-world systems, models are frequently updated as more data becomes available, and in addition to achieving high accuracy, the goal is to also maintain a low difference in predictions compared to the base model (i.e. predictive…
Federated learning (FL) has gained significant attention for enabling decentralized training on edge networks without exposing raw data. However, FL models remain susceptible to adversarial attacks and performance degradation in non-IID…
Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…
This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness. Recent works observed that Adversarial Training leads to robust models, whose learnt features appear to…
The efficacy of deep learning models has been called into question by the presence of adversarial examples. Addressing the vulnerability of deep learning models to adversarial examples is crucial for ensuring their continued development and…
Dataset distillation synthesizes compact datasets that enable models to achieve performance comparable to training on the original large-scale datasets. However, existing distillation methods overlook the robustness of the model, resulting…
Several existing works study either adversarial or natural distributional robustness of deep neural networks separately. In practice, however, models need to enjoy both types of robustness to ensure reliability. In this work, we bridge this…