English
Related papers

Related papers: Fortifying Toxic Speech Detectors Against Veiled T…

200 papers

Building reliable deception detectors for AI systems -- methods that could predict when an AI system is being strategically deceptive without necessarily requiring behavioural evidence -- would be valuable in mitigating risks from advanced…

Machine Learning · Computer Science 2025-12-17 Lewis Smith , Bilal Chughtai , Neel Nanda

Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-based classifiers are commonly employed to detect…

Cryptography and Security · Computer Science 2026-05-14 Nicolas Müller , Piotr Kawa , Adriana Stan , Thien-Phuc Doan , Souhwan Jung , Wei Herng Choong , Philip Sperl , Konstantin Böttinger

This paper reports on an experiment into text-based phishing detection using readily available resources and without the use of semantics. The developed algorithm is a modified version of previously published work that works with the same…

Computation and Language · Computer Science 2021-11-04 Gilchan Park , Julia M. Taylor

The rapid advancement of fake voice generation technology has ignited a race with detection systems, creating an urgent need to secure the audio ecosystem. However, existing benchmarks suffer from a critical limitation: they typically…

Sound · Computer Science 2025-10-20 Xutao Mao , Ke Li , Cameron Baird , Ezra Xuanru Tao , Dan Lin

Toxicity detection algorithms, originally designed with reactive content moderation in mind, are increasingly being deployed into proactive end-user interventions to moderate content. Through a socio-technical lens and focusing on contexts…

Human-Computer Interaction · Computer Science 2025-02-25 Mark Warner , Angelika Strohmayer , Matthew Higgs , Lynne Coventry

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…

Computation and Language · Computer Science 2021-07-27 Jiehang Zeng , Xiaoqing Zheng , Jianhan Xu , Linyang Li , Liping Yuan , Xuanjing Huang

When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-15 Han Zhu , Dongji Gao , Gaofeng Cheng , Daniel Povey , Pengyuan Zhang , Yonghong Yan

The growth of highly advanced Large Language Models (LLMs) constitutes a huge dual-use problem, making it necessary to create dependable AI-generated text detection systems. Modern detectors are notoriously vulnerable to adversarial…

Cryptography and Security · Computer Science 2025-10-06 Lekkala Sai Teja , Annepaka Yadagiri , Sangam Sai Anish , Siva Gopala Krishna Nuthakki , Partha Pakray

Online hate speech is an important issue that breaks the cohesiveness of online social communities and even raises public safety concerns in our societies. Motivated by this rising issue, researchers have developed many traditional machine…

Computation and Language · Computer Science 2021-03-23 Rui Cao , Roy Ka-Wei Lee , Tuan-Anh Hoang

As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural and adversarial data.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Qian Wang , Chen Li , Yuchen Luo , Hefei Ling , Shijuan Huang , Ruoxi Jia , Ning Yu

Audio is one of the most used ways of human communication, but at the same time it can be easily misused to trick people. With the revolution of AI, the related technologies are now accessible to almost everyone, thus making it simple for…

Voice Processing Systems (VPSes), now widely deployed, have been made significantly more accurate through the application of recent advances in machine learning. However, adversarial machine learning has similarly advanced and has been used…

Cryptography and Security · Computer Science 2019-04-12 Hadi Abdullah , Washington Garcia , Christian Peeters , Patrick Traynor , Kevin R. B. Butler , Joseph Wilson

Neural speech editing advancements have raised concerns about their misuse in spoofing attacks. Traditional partially edited speech corpora primarily focus on cut-and-paste edits, which, while maintaining speaker consistency, often…

Large language models (LLMs) excel in many diverse applications beyond language generation, e.g., translation, summarization, and sentiment analysis. One intriguing application is in text classification. This becomes pertinent in the realm…

Computation and Language · Computer Science 2024-03-14 Tharindu Kumarage , Amrita Bhattacharjee , Joshua Garland

Recently, tampered text detection has attracted increasing attention due to its essential role in information security. Although existing methods can detect the tampered text region, the interpretation of such detection remains unclear,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-16 Chenfan Qu , Jian Liu , Haoxing Chen , Baihan Yu , Jingjing Liu , Weiqiang Wang , Lianwen Jin

Today's generative neural networks allow the creation of high-quality synthetic speech at scale. While we welcome the creative use of this new technology, we must also recognize the risks. As synthetic speech is abused for monetary and…

Sound · Computer Science 2024-04-10 Konstantin Gasenzer , Moritz Wolter

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

Current methods of toxic language detection (TLD) typically rely on specific tokens to conduct decisions, which makes them suffer from lexical bias, leading to inferior performance and generalization. Lexical bias has both "useful" and…

Computation and Language · Computer Science 2024-06-04 Junyu Lu , Bo Xu , Xiaokun Zhang , Kaiyuan Liu , Dongyu Zhang , Liang Yang , Hongfei Lin

The rapid advancement of generative models has enabled the creation of increasingly stealthy synthetic voices, commonly referred to as audio deepfakes. A recent technique, FOICE [USENIX'24], demonstrates a particularly alarming capability:…

Cryptography and Security · Computer Science 2025-11-14 Nguyen Linh Bao Nguyen , Alsharif Abuadbba , Kristen Moore , Tingmin Wu

Recent advancements in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation.…

Computation and Language · Computer Science 2025-06-02 Andrea Pedrotti , Michele Papucci , Cristiano Ciaccio , Alessio Miaschi , Giovanni Puccetti , Felice Dell'Orletta , Andrea Esuli