English
Related papers

Related papers: LeakAgent: RL-based Red-teaming Agent for LLM Priv…

200 papers

Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive alignment efforts. Existing adversarial prompt generation…

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt…

Machine Learning · Computer Science 2025-10-07 Taeyoung Yun , Pierre-Luc St-Charles , Jinkyoo Park , Yoshua Bengio , Minsu Kim

As large language models (LLMs) are increasingly used for code generation, concerns over the security risks have grown substantially. Early research has primarily focused on red teaming, which aims to uncover and evaluate vulnerabilities…

Software Engineering · Computer Science 2025-10-22 Chengquan Guo , Yuzhou Nie , Chulin Xie , Zinan Lin , Wenbo Guo , Bo Li

As Large Language Models (LLMs) evolve into personal assistants with access to sensitive user data, they face a critical privacy challenge: while prior work has addressed output-level privacy, recent findings reveal that LLMs often leak…

Cryptography and Security · Computer Science 2025-11-24 Shourya Batra , Pierce Tillman , Samarth Gaggar , Shashank Kesineni , Kevin Zhu , Sunishchal Dev , Ashwinee Panda , Vasu Sharma , Maheep Chaudhary

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…

Computation and Language · Computer Science 2025-11-18 Xikang Yang , Biyu Zhou , Xuehai Tang , Jizhong Han , Songlin Hu

Large language models (LLMs) and AI agents are increasingly integrated into enterprise systems to access internal databases and generate context-aware responses. While such integration improves productivity and decision support, the model…

Cryptography and Security · Computer Science 2026-03-19 Ya-Ting Yang , Quanyan Zhu

We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. Existing AI safety approaches often rely on costly human evaluation…

Computation and Language · Computer Science 2025-10-13 Ali Asad , Stephen Obadinma , Radin Shayanfar , Xiaodan Zhu

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

Human-Computer Interaction · Computer Science 2025-10-07 Zhiping Zhang , Bingcan Guo , Tianshi Li

Automated red-teaming has emerged as a scalable approach for auditing Large Language Models (LLMs) prior to deployment, yet existing approaches lack mechanisms to efficiently adapt to model-specific vulnerabilities at inference. We…

Computation and Language · Computer Science 2026-05-19 Christos Ziakas , Nicholas Loo , Nishita Jain , Alessandra Russo

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to leverage external knowledge, but also exposes valuable RAG databases to leakage attacks. As RAG systems grow more complex and LLMs exhibit stronger…

Cryptography and Security · Computer Science 2026-05-08 Maosen Zhang , Jianshuo Dong , Boting Lu , Wenyue Li , Xiaoping Zhang , Tianwei Zhang , Han Qiu

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

Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as…

Cryptography and Security · Computer Science 2024-10-01 Zeguan Xiao , Yan Yang , Guanhua Chen , Yun Chen

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…

Artificial Intelligence · Computer Science 2026-02-26 Wenkai Li , Liwen Sun , Zhenxiang Guan , Xuhui Zhou , Maarten Sap

Recent breakthroughs in natural language processing (NLP) have permitted the synthesis and comprehension of coherent text in an open-ended way, therefore translating the theoretical algorithms into practical applications. The large language…

Computation and Language · Computer Science 2023-05-30 Terry Yue Zhuo , Yujin Huang , Chunyang Chen , Zhenchang Xing

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

Cryptography and Security · Computer Science 2026-05-27 Faruk Alpay , Taylan Alpay

Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing effective protection against many modes of attack prompts…

Computation and Language · Computer Science 2025-03-03 Seanie Lee , Minsu Kim , Lynn Cherif , David Dobre , Juho Lee , Sung Ju Hwang , Kenji Kawaguchi , Gauthier Gidel , Yoshua Bengio , Nikolay Malkin , Moksh Jain

Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…

Cryptography and Security · Computer Science 2026-04-22 Jonathan Evertz , Merlin Chlosta , Lea Schönherr , Thorsten Eisenhofer

Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy.…

Computation and Language · Computer Science 2026-02-17 Yuhan Cheng , Hancheng Ye , Hai Helen Li , Jingwei Sun , Yiran Chen

Red-teaming has been a widely adopted way to evaluate the harmfulness of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful agent disregarding the harmfulness of the query. Existing…

Computation and Language · Computer Science 2023-11-14 Rishabh Bhardwaj , Soujanya Poria

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests…

Computation and Language · Computer Science 2025-03-03 Shiwen Ni , Xiangtao Kong , Chengming Li , Xiping Hu , Ruifeng Xu , Jia Zhu , Min Yang