English
Related papers

Related papers: LLM-Based Adversarial Persuasion Attacks on Fact-C…

200 papers

Adversarial attacks reveal important vulnerabilities and flaws of trained models. One potent type of attack are universal adversarial triggers, which are individual n-grams that, when appended to instances of a class under attack, can trick…

Computation and Language · Computer Science 2020-09-18 Pepa Atanasova , Dustin Wright , Isabelle Augenstein

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

Cryptography and Security · Computer Science 2026-05-25 Xueyi Li , Zhuoneng Zhou , Zitao Liu , Yongdong Wu

Automated Fact-Checking (AFC) is the automated verification of claim accuracy. AFC is crucial in discerning truth from misinformation, especially given the huge amounts of content are generated online daily. Current research focuses on…

Computation and Language · Computer Science 2025-04-08 Islam Eldifrawi , Shengrui Wang , Amine Trabelsi

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Machine Learning · Computer Science 2025-10-08 Zizhao Wang , Dingcheng Li , Vaishakh Keshava , Phillip Wallis , Ananth Balashankar , Peter Stone , Lukas Rutishauser

Large Language Models (LLMs) are increasingly used in applications where the model selects from competing third-party content, such as in LLM-powered search engines or chatbot plugins. In this paper, we introduce Preference Manipulation…

Cryptography and Security · Computer Science 2024-07-03 Fredrik Nestaas , Edoardo Debenedetti , Florian Tramèr

Large Language Models (LLMs) are increasingly used in education, yet their default helpfulness often conflicts with pedagogical principles. Prior work evaluates pedagogical quality via answer leakage-the disclosure of complete solutions…

Cryptography and Security · Computer Science 2026-04-22 Jin Zhao , Marta Knežević , Tanja Käser

Rapid LLM advancements heighten fake news risks by enabling the automatic generation of increasingly sophisticated misinformation. Previous detection methods, including fine-tuned small models or LLM-based detectors, often struggle with its…

Computation and Language · Computer Science 2025-08-28 Chong Tian , Qirong Ho , Xiuying Chen

The last decade has seen the rise of Adversarial Machine Learning (AML). This discipline studies how to manipulate data to fool inference engines, and how to protect those systems against such manipulation attacks. Extensive work on attacks…

Machine Learning · Statistics 2021-10-22 Roi Naveiro

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

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

Artificial Intelligence · Computer Science 2025-05-20 Lili Zhang , Haomiaomiao Wang , Long Cheng , Libao Deng , Tomas Ward

Model quantization is critical for deploying large language models (LLMs) on resource-constrained hardware, yet recent work has revealed severe security risks that benign LLMs in full precision may exhibit malicious behaviors after…

Cryptography and Security · Computer Science 2026-01-07 Dinghong Song , Zhiwei Xu , Hai Wan , Xibin Zhao , Pengfei Su , Dong Li

Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adversarial attacks remain poorly understood. We present a systematic benchmark of…

Computation and Language · Computer Science 2026-05-26 Lingyao Li , Junjie Xiong , Changjia Zhu , Runlong Yu , Chen Chen , Junyu Wang , Renkai Ma , Zhicong Lu

Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an…

Artificial Intelligence · Computer Science 2024-10-11 Tomas Bueno Momcilovic , Beat Buesser , Giulio Zizzo , Mark Purcell , Dian Balta

Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some…

Computation and Language · Computer Science 2023-12-22 Andy Zou , Zifan Wang , Nicholas Carlini , Milad Nasr , J. Zico Kolter , Matt Fredrikson

Large Language Models (LLMs) are vulnerable to jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires a time-consuming search for adversarial prompts, whereas automatic adversarial…

Cryptography and Security · Computer Science 2025-06-04 Anselm Paulus , Arman Zharmagambetov , Chuan Guo , Brandon Amos , Yuandong Tian

The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques…

Machine Learning · Computer Science 2018-02-21 Nicholas Carlini , Guy Katz , Clark Barrett , David L. Dill

Background: Deception detection through analysing language is a promising avenue using both human judgments and automated machine learning judgments. For both forms of credibility assessment, automated adversarial attacks that rewrite…

Computation and Language · Computer Science 2025-06-03 Bennett Kleinberg , Riccardo Loconte , Bruno Verschuere

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Artificial Intelligence · Computer Science 2023-10-31 Leo Schwinn , David Dobre , Stephan Günnemann , Gauthier Gidel

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…

Machine Learning · Computer Science 2019-11-19 Rey Reza Wiyatno , Anqi Xu , Ousmane Dia , Archy de Berker

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…

‹ Prev 1 3 4 5 6 7 10 Next ›