English
Related papers

Related papers: Build it Break it Fix it for Dialogue Safety: Robu…

200 papers

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. Dialogue systems are increasingly being designed to move beyond just imitating conversation and also…

Computation and Language · Computer Science 2021-11-03 Atharv Singh Patlan , Shiven Tripathi , Shubham Korde

We investigate the adversarial robustness of LLMs in transfer learning scenarios. Through comprehensive experiments on multiple datasets (MBIB Hate Speech, MBIB Political Bias, MBIB Gender Bias) and various model architectures (BERT,…

Computation and Language · Computer Science 2025-06-10 Bohdan Turbal , Anastasiia Mazur , Jiaxu Zhao , Mykola Pechenizkiy

Attackers create adversarial text to deceive both human perception and the current AI systems to perform malicious purposes such as spam product reviews and fake political posts. We investigate the difference between the adversarial and the…

Computation and Language · Computer Science 2019-12-20 Hoang-Quoc Nguyen-Son , Tran Phuong Thao , Seira Hidano , Shinsaku Kiyomoto

Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. As a countermeasure, backdoor detection methods…

Computation and Language · Computer Science 2025-09-23 Jun Yan , Wenjie Jacky Mo , Xiang Ren , Robin Jia

As LLMs gain persuasive capabilities through extended dialogues, they create new opportunities for studying adversarial conversational behavior in extended interaction settings that traditional single-turn safety evaluations fail to…

Computation and Language · Computer Science 2026-05-29 Xiangzhe Yuan , Zhenhao Zhang , Haoming Tang , Siying Hu

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adversarial training…

Computation and Language · Computer Science 2022-03-25 Hanjie Chen , Yangfeng Ji

Dialogue systems play an increasingly important role in various aspects of our daily life. It is evident from recent research that dialogue systems trained on human conversation data are biased. In particular, they can produce responses…

Computation and Language · Computer Science 2020-11-03 Haochen Liu , Wentao Wang , Yiqi Wang , Hui Liu , Zitao Liu , Jiliang Tang

Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text. However, with their rising prominence, the…

Cryptography and Security · Computer Science 2024-03-26 Arijit Ghosh Chowdhury , Md Mofijul Islam , Vaibhav Kumar , Faysal Hossain Shezan , Vaibhav Kumar , Vinija Jain , Aman Chadha

Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning in real-world…

Machine Learning · Computer Science 2024-08-13 Thanh Nguyen , Tung M. Luu , Tri Ton , Chang D. Yoo

The widespread use of social media necessitates reliable and efficient detection of offensive content to mitigate harmful effects. Although sophisticated models perform well on individual datasets, they often fail to generalize due to…

Computation and Language · Computer Science 2024-10-08 Huy Nghiem , Hal Daumé

We introduce the task of implicit offensive text detection in dialogues, where a statement may have either an offensive or non-offensive interpretation, depending on the listener and context. We argue that reasoning is crucial for…

Computation and Language · Computer Science 2022-04-25 Qiang Zhang , Jason Naradowsky , Yusuke Miyao

Large Language Models (LLMs) have rapidly evolved over the past few years and are currently evaluated for their efficacy within the domain of offensive cyber-security. While initial forays showcase the potential of LLMs to enhance security…

Cryptography and Security · Computer Science 2025-06-11 Andreas Happe , Jürgen Cito

Detecting persuasion in argumentative text is a challenging task with important implications for understanding human communication. This work investigates the role of persuasion strategies - such as Attack on reputation, Distraction, and…

Computation and Language · Computer Science 2026-01-16 Tiziano Labruna , Arkadiusz Modzelewski , Giorgio Satta , Giovanni Da San Martino

An increasingly common socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help detect these deceptive…

Computation and Language · Computer Science 2025-06-06 Wichayaporn Wongkamjan , Yanze Wang , Feng Gu , Denis Peskoff , Jonathan K. Kummerfeld , Jonathan May , Jordan Lee Boyd-Graber

Reinforcement learning based dialogue policies are typically trained in interaction with a user simulator. To obtain an effective and robust policy, this simulator should generate user behaviour that is both realistic and varied. Current…

Computation and Language · Computer Science 2023-06-02 Simon Keizer , Caroline Dockes , Norbert Braunschweiler , Svetlana Stoyanchev , Rama Doddipatla

In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning. We create a…

Computation and Language · Computer Science 2022-05-25 Zhao Meng , Yihan Dong , Mrinmaya Sachan , Roger Wattenhofer

While state-of-the-art language models have achieved impressive results, they remain susceptible to inference-time adversarial attacks, such as adversarial prompts generated by red teams arXiv:2209.07858. One approach proposed to improve…

Computation and Language · Computer Science 2024-01-12 Steffi Chern , Zhen Fan , Andy Liu

Speaker embedding based zero-shot Text-to-Speech (TTS) systems enable high-quality speech synthesis for unseen speakers using minimal data. However, these systems are vulnerable to adversarial attacks, where an attacker introduces…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-07 Ze Li , Yao Shi , Yunfei Xu , Ming Li

Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods. Current…

Computation and Language · Computer Science 2020-10-05 Linyang Li , Ruotian Ma , Qipeng Guo , Xiangyang Xue , Xipeng Qiu