Related papers: Toward Adversarial Training on Contextualized Lang…

Adversarial Training (AT), which is commonly accepted as one of the most effective approaches defending against adversarial examples, can largely harm the standard performance, thus has limited usefulness on industrial-scale production and…

In this paper we proposed a novel Adversarial Training (AT) approach for end-to-end speech recognition using a Criticizing Language Model (CLM). In this way the CLM and the automatic speech recognition (ASR) model can challenge and learn…

For years, adversarial training has been extensively studied in natural language processing (NLP) settings. The main goal is to make models robust so that similar inputs derive in semantically similar outcomes, which is not a trivial…

Adversarial training (AT) as a regularization method has proved its effectiveness in various tasks, such as image classification and text classification. Though there are successful applications of AT in many tasks of natural language…

Recent work has shown that language models' refusal behavior is primarily encoded in a single direction in their latent space, making it vulnerable to targeted attacks. Although Latent Adversarial Training (LAT) attempts to improve…

Deep learning models exhibit a preference for statistical fitting over logical reasoning. Spurious correlations might be memorized when there exists statistical bias in training data, which severely limits the model performance especially…

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…

In recent years, large pre-trained language models (PLMs) have achieved remarkable performance on many natural language processing benchmarks. Despite their success, prior studies have shown that PLMs are vulnerable to attacks from…

Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few years. Algorithm design of AT and its variants are focused on…

Adversarial training (AT) as a regularization method has proved its effectiveness on various tasks. Though there are successful applications of AT on some NLP tasks, the distinguishing characteristics of NLP tasks have not been exploited.…

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that…

Adversarial training (AT) is a regularization method that can be used to improve the robustness of neural network methods by adding small perturbations in the training data. We show how to use AT for the tasks of entity recognition and…

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…

Generalization and robustness are both key desiderata for designing machine learning methods. Adversarial training can enhance robustness, but past work often finds it hurts generalization. In natural language processing (NLP), pre-training…

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…

Extensive research demonstrates that Deep Reinforcement Learning (DRL) models are susceptible to adversarially constructed inputs (i.e., adversarial examples), which can mislead the agent to take suboptimal or unsafe actions. Recent methods…

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

Self-supervised learning approach like contrastive learning is attached great attention in natural language processing. It uses pairs of training data augmentations to build a classification task for an encoder with well representation…

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…

Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning. Variants of this method have been used as regularization mechanisms to achieve SOTA results on NLP benchmarks, and…