English
Related papers

Related papers: Differential Robustness in Transformer Language Mo…

200 papers

As the deployment of NLP systems in critical applications grows, ensuring the robustness of large language models (LLMs) against adversarial attacks becomes increasingly important. Large language models excel in various NLP tasks but remain…

Computation and Language · Computer Science 2024-05-03 Zhenning Yang , Ryan Krawec , Liang-Yuan Wu

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive…

Cryptography and Security · Computer Science 2026-03-19 Taiwo Onitiju , Iman Vakilinia

There has been significant progress in recent years in the field of Natural Language Processing thanks to the introduction of the Transformer architecture. Current state-of-the-art models, via a large number of parameters and pre-training…

Artificial Intelligence · Computer Science 2020-03-31 Carlos Aspillaga , Andrés Carvallo , Vladimir Araujo

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While…

Computation and Language · Computer Science 2023-07-13 Yahan Yang , Soham Dan , Dan Roth , Insup Lee

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Computation and Language · Computer Science 2025-10-08 Harethah Abu Shairah , Hasan Abed Al Kader Hammoud , Bernard Ghanem , George Turkiyyah

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Machine Learning · Computer Science 2025-06-06 Nikolaus Howe , Ian McKenzie , Oskar Hollinsworth , Michał Zajac , Tom Tseng , Aaron Tucker , Pierre-Luc Bacon , Adam Gleave

Deep Neural Networks have taken Natural Language Processing by storm. While this led to incredible improvements across many tasks, it also initiated a new research field, questioning the robustness of these neural networks by attacking…

Computation and Language · Computer Science 2021-09-16 Jens Hauser , Zhao Meng , Damián Pascual , Roger Wattenhofer

Transformers have been shown to be able to perform deductive reasoning on a logical rulebase containing rules and statements written in English natural language. While the progress is promising, it is currently unclear if these models…

Computation and Language · Computer Science 2022-11-09 Soumya Sanyal , Zeyi Liao , Xiang Ren

Large Language Models (LLMs) have become vital tools in software development tasks such as code generation, completion, and analysis. As their integration into workflows deepens, ensuring robustness against vulnerabilities especially those…

Software Engineering · Computer Science 2025-07-21 Yang Liu , Armstrong Foundjem , Foutse Khomh , Heng Li

Large Language Models (LLMs) are trained on Web data that might contain spelling errors made by humans. But do they become robust to similar real-world noise? In this paper, we investigate the effect of real-world spelling mistakes on the…

Computation and Language · Computer Science 2025-01-15 Amirhossein Aliakbarzadeh , Lucie Flek , Akbar Karimi

We conduct a thorough study to diagnose the behaviors of pre-trained language encoders (ELMo, BERT, and RoBERTa) when confronted with natural grammatical errors. Specifically, we collect real grammatical errors from non-native speakers and…

Computation and Language · Computer Science 2020-05-13 Fan Yin , Quanyu Long , Tao Meng , Kai-Wei Chang

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

Computation and Language · Computer Science 2024-03-19 Javad Rafiei Asl , Prajwal Panzade , Eduardo Blanco , Daniel Takabi , Zhipeng Cai

Ensuring the security of large language models (LLMs) is an ongoing challenge despite their widespread popularity. Developers work to enhance LLMs security, but vulnerabilities persist, even in advanced versions like GPT-4. Attackers…

Cryptography and Security · Computer Science 2023-12-19 Aysan Esmradi , Daniel Wankit Yip , Chun Fai Chan

To combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier. Our word recognition models build upon the RNN semi-character architecture, introducing several new backoff…

Computation and Language · Computer Science 2019-08-30 Danish Pruthi , Bhuwan Dhingra , Zachary C. Lipton

Large Language Models (LLMs) undergo continuous updates to improve user experience. However, prior research on the security and safety implications of LLMs has primarily focused on their specific versions, overlooking the impact of…

Cryptography and Security · Computer Science 2026-03-11 Yugeng Liu , Tianshuo Cong , Zhengyu Zhao , Michael Backes , Yun Shen , Yang Zhang

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…

Computation and Language · Computer Science 2024-02-07 Norah Alshahrani , Saied Alshahrani , Esma Wali , Jeanna Matthews

This paper investigates the effectiveness of large language models (LLMs) in email spam detection by comparing prominent models from three distinct families: BERT-like, Sentence Transformers, and Seq2Seq. Additionally, we examine…

Computation and Language · Computer Science 2023-05-09 Maxime Labonne , Sean Moran

Background: Cyber-attacks have evolved rapidly in recent years, many individuals and business owners have been affected by cyber-attacks in various ways. Cyber-attacks include various threats such as ransomware, malware, phishing, and…

Cryptography and Security · Computer Science 2026-01-13 Keerthi Kumar. M , Swarun Kumar Joginpelly , Sunil Khemka , Lakshmi. S R , Navin Chhibber

With the increasing use of large language models (LLMs), ensuring reliable performance in diverse, real-world environments is essential. Despite their remarkable achievements, LLMs often struggle with adversarial inputs, significantly…

Computation and Language · Computer Science 2024-06-18 Yuqing Wang , Yun Zhao

Large Language Models (LLMs) have recently demonstrated significant potential in time series forecasting, offering impressive capabilities in handling complex temporal data. However, their robustness and reliability in real-world…

Machine Learning · Computer Science 2025-03-14 Fuqiang Liu , Sicong Jiang , Luis Miranda-Moreno , Seongjin Choi , Lijun Sun