相关论文: Adversarial Stylometry in the Wild: Transferable L…

As the issues of privacy and trust are receiving increasing attention within the research community, various attempts have been made to anonymize textual data. A significant subset of these approaches incorporate differentially private…

Despite the strong performance of deep neural networks in modern Web and language applications, they remain vulnerable to adversarial attacks, especially transferable attacks that generate adversarial examples using surrogate models without…

The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses…

The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to…

Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks. In this work, we further reveal this…

Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research on generating adversarial attacks and building defense…

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting prompts that induce LLMs to generate harmful content. Current methods…

Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly…

Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily…

Recent advances in natural language generation have introduced powerful language models with high-quality output text. However, this raises concerns about the potential misuse of such models for malicious purposes. In this paper, we study…

This paper introduces a novel adversarial algorithm for attacking the state-of-the-art speech-to-text systems, namely DeepSpeech, Kaldi, and Lingvo. Our approach is based on developing an extension for the conventional distortion condition…

Deep neural networks were significantly vulnerable to adversarial examples manipulated by malicious tiny perturbations. Although most conventional adversarial attacks ensured the visual imperceptibility between adversarial examples and…

This paper presents a framework which enables a user to more easily make corrections to adversarial texts. While attack algorithms have been demonstrated to automatically build adversaries, changes made by the algorithms can often have poor…

Authorship attribution aims to identify the author of a text based on the stylometric analysis. Authorship obfuscation, on the other hand, aims to protect against authorship attribution by modifying a text's style. In this paper, we…

Although temporal tagging is still dominated by rule-based systems, there have been recent attempts at neural temporal taggers. However, all of them focus on monolingual settings. In this paper, we explore multilingual methods for the…

With the rapid advancement and widespread application of vision-language pre-training (VLP) models, their vulnerability to adversarial attacks has become a critical concern. In general, the adversarial examples can typically be designed to…

Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. We show that demographic information of authors is encoded in -- and can be recovered from --…

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…