Related papers: Adversarial Training for Improving Model Robustnes…
Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attack over the examples…
Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively…
Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new attacks over time. A natural solution is to adapt the defended…
Neural ranking models (NRMs) have shown great success in information retrieval (IR). But their predictions can easily be manipulated using adversarial examples, which are crafted by adding imperceptible perturbations to legitimate…
Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustness through Dynamic Ensemble Learning (ARDEL), a novel scheme…
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…
Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…
Model-agnostic meta-learning (MAML) has emerged as one of the most successful meta-learning techniques in few-shot learning. It enables us to learn a meta-initialization} of model parameters (that we call meta-model) to rapidly adapt to new…
Deep neural networks are susceptible to adversarial examples, posing a significant security risk in critical applications. Adversarial Training (AT) is a well-established technique to enhance adversarial robustness, but it often comes at…
Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy machine learning systems. Current robust training methods such as adversarial training explicitly uses an "attack"…
In recent years, there has been an explosion of research into developing more robust deep neural networks against adversarial examples. Adversarial training appears as one of the most successful methods. To deal with both the robustness…
With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…
The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention. Inspired by the success of vision-language foundation models, previous efforts achieved zero-shot adversarial…
Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of…
The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained…
Adversarial training is a promising strategy for enhancing model robustness against adversarial attacks. However, its impact on generalization under substantial data distribution shifts in audio classification remains largely unexplored. To…
In this paper we study leveraging confidence information induced by adversarial training to reinforce adversarial robustness of a given adversarially trained model. A natural measure of confidence is $\|F({\bf x})\|_\infty$ (i.e. how…
Pre-trained language models (PLMs) have driven substantial progress in natural language processing but remain vulnerable to adversarial attacks, raising concerns about their robustness in real-world applications. Previous studies have…
Adversarial training has been widely acknowledged as the most effective method to improve the adversarial robustness against adversarial examples for Deep Neural Networks (DNNs). So far, most existing works focus on enhancing the overall…
The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks. We cast the spotlight on the underexplored task of Natural Language Inference (NLI), since…