Related papers: DSRM: Boost Textual Adversarial Training with Dist…
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…
Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We…
Deep neural networks are vulnerable to adversarial examples. Adversarial training (AT) is an effective defense against adversarial examples. However, AT is prone to overfitting which degrades robustness substantially. Recently, data…
We present a new algorithm to learn a deep neural network model robust against adversarial attacks. Previous algorithms demonstrate an adversarially trained Bayesian Neural Network (BNN) provides improved robustness. We recognize the…
With the increasing deployment of deep neural networks in safety-critical applications such as self-driving cars, medical imaging, anomaly detection, etc., adversarial robustness has become a crucial concern in the reliability of these…
In this paper we propose a new family of algorithms, ATENT, for training adversarially robust deep neural networks. We formulate a new loss function that is equipped with an additional entropic regularization. Our loss function considers…
We study a robust alternative to empirical risk minimization called distributionally robust learning (DRL), in which one learns to perform against an adversary who can choose the data distribution from a specified set of distributions. We…
In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…
It is shown that many published models for the Stanford Question Answering Dataset (Rajpurkar et al., 2016) lack robustness, suffering an over 50% decrease in F1 score during adversarial evaluation based on the AddSent (Jia and Liang, 2017)…
Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develops a full-link security enhancement framework, which describes "input risk perception -…
Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled data is scarce. In this paper, we introduce a novel…
In recent years, Deep Reinforcement Learning (DRL) has become a popular paradigm in machine learning due to its successful applications to real-world and complex systems. However, even the state-of-the-art DRL models have been shown to…
Despite significant advancements in deep reinforcement learning (DRL)-based autonomous driving policies, these policies still exhibit vulnerability to adversarial attacks. This vulnerability poses a formidable challenge to the practical…
Adversarial training has been actively studied in recent computer vision research to improve the robustness of models. However, due to the huge computational cost of generating adversarial samples, adversarial training methods are often…
Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. Structured pruning reduces model size and speeds up inference but often causes uneven degradation across…
Deep neural networks for natural language processing tasks are vulnerable to adversarial input perturbations. In this paper, we present a versatile language for programmatically specifying string transformations -- e.g., insertions,…
Learning robust models under adversarial settings is widely recognized as requiring a considerably large number of training samples. Recent work proposes semi-supervised adversarial training (SSAT), which utilizes external unlabeled or…
Text classification systems have been proven vulnerable to adversarial text examples, modified versions of the original text examples that are often unnoticed by human eyes, yet can force text classification models to alter their…
Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…
Deep Neural Networks, despite their great success in diverse domains, are provably sensitive to small perturbations on correctly classified examples and lead to erroneous predictions. Recently, it was proposed that this behavior can be…