English
Related papers

Related papers: Efficient Black-Box Adversarial Attacks on Neural …

200 papers

The burgeoning progress in the field of Large Language Models (LLMs) heralds significant benefits due to their unparalleled capacities. However, it is critical to acknowledge the potential misuse of these models, which could give rise to a…

Computation and Language · Computer Science 2023-08-07 Haolan Zhan , Xuanli He , Qiongkai Xu , Yuxiang Wu , Pontus Stenetorp

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…

Cryptography and Security · Computer Science 2023-05-01 Jiazhao Li , Yijin Yang , Zhuofeng Wu , V. G. Vinod Vydiswaran , Chaowei Xiao

Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a…

Computation and Language · Computer Science 2024-01-09 Tom Roth , Yansong Gao , Alsharif Abuadbba , Surya Nepal , Wei Liu

We propose the first character-level white-box adversarial attack method against transformer models. The intuition of our method comes from the observation that words are split into subtokens before being fed into the transformer models and…

Computation and Language · Computer Science 2022-11-01 Aiwei Liu , Honghai Yu , Xuming Hu , Shu'ang Li , Li Lin , Fukun Ma , Yawen Yang , Lijie Wen

In this paper, we present an effective method to craft text adversarial samples, revealing one important yet underestimated fact that DNN-based text classifiers are also prone to adversarial sample attack. Specifically, confronted with…

Cryptography and Security · Computer Science 2019-01-08 Bin Liang , Hongcheng Li , Miaoqiang Su , Pan Bian , Xirong Li , Wenchang Shi

Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulously altered inputs. Adversarial texts, however, are distinct…

Machine Learning · Computer Science 2025-01-24 Shakila Mahjabin Tonni , Pedro Faustini , Mark Dras

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Computation and Language · Computer Science 2025-10-27 Bushra Sabir , Yansong Gao , Alsharif Abuadbba , M. Ali Babar

Human evaluations are typically considered the gold standard in natural language generation, but as models' fluency improves, how well can evaluators detect and judge machine-generated text? We run a study assessing non-experts' ability to…

Computation and Language · Computer Science 2021-07-08 Elizabeth Clark , Tal August , Sofia Serrano , Nikita Haduong , Suchin Gururangan , Noah A. Smith

Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. Consequently, they are prone to generating non-normative text (i.e. in violation of social norms). We introduce a…

Computation and Language · Computer Science 2020-11-02 Xiangyu Peng , Siyan Li , Spencer Frazier , Mark Riedl

Several years of research have shown that machine-learning systems are vulnerable to adversarial examples, both in theory and in practice. Until now, such attacks have primarily targeted visual models, exploiting the gap between human and…

Computation and Language · Computer Science 2021-12-14 Nicholas Boucher , Ilia Shumailov , Ross Anderson , Nicolas Papernot

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…

Machine Learning · Computer Science 2021-09-23 Liping Yuan , Xiaoqing Zheng , Yi Zhou , Cho-Jui Hsieh , Kai-wei Chang

The rapid adoption of generative language models has brought about substantial advancements in digital communication, while simultaneously raising concerns regarding the potential misuse of AI-generated content. Although numerous detection…

Computation and Language · Computer Science 2023-07-13 Weixin Liang , Mert Yuksekgonul , Yining Mao , Eric Wu , James Zou

Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations that mislead deep learning models. While adversarial example detection offers a lightweight…

Computation and Language · Computer Science 2026-03-16 He Zhu , Yanshu Li , Wen Liu , Haitian Yang

Machine-Generated Text (MGT) detection aims to identify a piece of text as machine or human written. Prior work has primarily formulated MGT detection as a binary classification task over an entire document, with limited work exploring…

Computation and Language · Computer Science 2024-06-12 Zhongping Zhang , Wenda Qin , Bryan A. Plummer

Large language models can produce convincing "fake text" in domains such as academic writing, product reviews, and political news. Many approaches have been investigated for the detection of artificially generated text. While this may seem…

Computation and Language · Computer Science 2025-06-27 Andrea McGlinchey , Peter J Barclay

Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in…

Artificial Intelligence · Computer Science 2023-06-30 Edoardo Mosca , Shreyash Agarwal , Javier Rando , Georg Groh

Many natural language related applications involve text generation, created by humans or machines. While in many of those applications machines support humans, yet in few others, (e.g. adversarial machine learning, social bots and trolls)…

Computation and Language · Computer Science 2022-12-23 Jesus Guerrero , Gongbo Liang , Izzat Alsmadi

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Cryptography and Security · Computer Science 2022-10-21 You Guo , Jun Wang , Trevor Cohn

Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception,…

Cryptography and Security · Computer Science 2025-07-23 Eldor Abdukhamidov , Tamer Abuhmed , Joanna C. S. Santos , Mohammed Abuhamad

Despite considerable progress in the development of machine-text detectors, it has been suggested that the problem is inherently hard, and therefore, that stakeholders should proceed under the assumption that machine-generated text cannot…

Computation and Language · Computer Science 2025-09-30 Rafael Rivera Soto , Barry Chen , Nicholas Andrews