English
Related papers

Related papers: ToxSearch: Evolving Prompts for Toxicity Search in…

200 papers

As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in submissions to manipulate outcomes, poses a critical threat…

Computation and Language · Computer Science 2026-05-29 Yuan Xin , Yixuan Weng , Minjun Zhu , Ying Ling , Chengwei Qin , Michael Backes , Yue Zhang , Linyi Yang

Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities…

Computation and Language · Computer Science 2026-01-16 Vahideh Zolfaghari

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Computation and Language · Computer Science 2026-04-29 Nirmalendu Prakash , Yeo Wei Jie , Amir Abdullah , Ranjan Satapathy , Erik Cambria , Roy Ka Wei Lee

Most large language models (LLMs) are sensitive to prompts, and another synonymous expression or a typo may lead to unexpected results for the model. Composing an optimal prompt for a specific demand lacks theoretical support and relies…

Computation and Language · Computer Science 2024-06-18 Zhenyu Zhang , Bingguang Hao , Jinpeng Li , Zekai Zhang , Dongyan Zhao

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

Recent NLP literature pays little attention to the robustness of toxicity language predictors, while these systems are most likely to be used in adversarial contexts. This paper presents a novel adversarial attack, \texttt{ToxicTrap},…

Computation and Language · Computer Science 2024-04-16 Dmitriy Bespalov , Sourav Bhabesh , Yi Xiang , Liutong Zhou , Yanjun Qi

Detecting hate speech and offensive language is essential for maintaining a safe and respectful digital environment. This study examines the limitations of state-of-the-art large language models (LLMs) in identifying offensive content…

Computation and Language · Computer Science 2024-06-19 Yunze Xiao , Yujia Hu , Kenny Tsu Wei Choo , Roy Ka-wei Lee

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

Cryptography and Security · Computer Science 2025-07-22 Pengfei Du

Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working mechanisms of safety prompts have not been unraveled yet,…

Machine Learning · Computer Science 2024-06-04 Chujie Zheng , Fan Yin , Hao Zhou , Fandong Meng , Jie Zhou , Kai-Wei Chang , Minlie Huang , Nanyun Peng

Detecting toxic content using language models is crucial yet challenging. While substantial progress has been made in English, toxicity detection in French remains underdeveloped, primarily due to the lack of culturally relevant,…

Computation and Language · Computer Science 2026-04-21 Axel Delaval , Shujian Yang , Haicheng Wang , Han Qiu , Jialiang Lu

Multimodal large language models (MLLMs) are increasingly used in real world applications, yet their safety under adversarial conditions remains underexplored. This study evaluates the harmlessness of four leading MLLMs (GPT-4o, Claude…

Computation and Language · Computer Science 2025-11-25 Madison Van Doren , Casey Ford

Large language models remain vulnerable to adversarial prompts that elicit harmful outputs. Existing safety paradigms typically couple red-teaming and post-training in a closed, policy-centric loop, causing attack discovery to suffer from…

Cryptography and Security · Computer Science 2026-05-14 Xiaozhe Zhang , Chaozhuo Li , Hui Liu , Shaocheng Yan , Bingyu Yan , Qiwei Ye , Haoliang Li

In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the…

Cryptography and Security · Computer Science 2024-08-23 Jiawei Zhao , Kejiang Chen , Xiaojian Yuan , Weiming Zhang

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

Cryptography and Security · Computer Science 2024-06-14 Xuan Chen , Yuzhou Nie , Lu Yan , Yunshu Mao , Wenbo Guo , Xiangyu Zhang

Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in…

Computation and Language · Computer Science 2024-09-16 Zeyu Yang , Zhao Meng , Xiaochen Zheng , Roger Wattenhofer

Large language models (LLMs) have revolutionized NLP research. Notably, in-context learning enables their use as evaluation metrics for natural language generation, making them particularly advantageous in low-resource scenarios and…

Computation and Language · Computer Science 2024-11-19 Christoph Leiter , Steffen Eger

Achieving both high safety and high usefulness simultaneously in large language models has become a critical challenge in recent years.Models often exhibit unsafe behavior or adopt an overly cautious approach leading to frequent overrefusal…

Computation and Language · Computer Science 2025-06-17 Batuhan K. Karaman , Ishmam Zabir , Alon Benhaim , Vishrav Chaudhary , Mert R. Sabuncu , Xia Song

Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation (RAG) allows…

Cryptography and Security · Computer Science 2026-04-13 Dennis Rall , Bernhard Bauer , Mohit Mittal , Thomas Fraunholz

Large language model (LLM) based search agents iteratively generate queries, retrieve external information, and reason to answer open-domain questions. While researchers have primarily focused on improving their utility, their safety…

Computation and Language · Computer Science 2026-03-24 Qiusi Zhan , Angeline Budiman-Chan , Abdelrahman Zayed , Xingzhi Guo , Daniel Kang , Joo-Kyung Kim

The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval. However, these systems are vulnerable to adversarial attacks, especially ranking manipulation attacks,…

Computation and Language · Computer Science 2025-05-19 Xiyang Hu