English
Related papers

Related papers: Breaking ReAct Agents: Foot-in-the-Door Attack Wil…

200 papers

Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human…

Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into external observations such as tool-returned data, webpages, or MCP context, causing harmful…

Artificial Intelligence · Computer Science 2026-05-28 Yongxiang Li , Moxin Li , Zhixin Ma , Fengbin Zhu , Dongrui Liu , Wenjie Wang , Fuli Feng

Large Language Models (LLMs) have demonstrated exceptional proficiency in instruction-following, becoming increasingly crucial across various applications. However, this capability brings with it the risk of prompt injection attacks, where…

Computation and Language · Computer Science 2023-11-28 Zekun Li , Baolin Peng , Pengcheng He , Xifeng Yan

Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e.g., via byte…

Computation and Language · Computer Science 2024-07-29 Nilanjana Das , Edward Raff , Manas Gaur

We demonstrate how AI-powered cybersecurity tools can be turned against themselves through prompt injection attacks. Prompt injection is reminiscent of cross-site scripting (XSS): malicious text is hidden within seemingly trusted content,…

Cryptography and Security · Computer Science 2025-11-18 Víctor Mayoral-Vilches , Per Mannermaa Rynning

Continuing advances in Large Language Models (LLMs) in artificial intelligence offer important capacities in intuitively accessing and using medical knowledge in many contexts, including education and training as well as assessment and…

Computation and Language · Computer Science 2024-08-01 Roma Shusterman , Allison C. Waters , Shannon O`Neill , Phan Luu , Don M. Tucker

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose…

Computation and Language · Computer Science 2026-04-07 Wenhui Zhu , Xuanzhao Dong , Xiwen Chen , Rui Cai , Peijie Qiu , Zhipeng Wang , Oana Frunza , Shao Tang , Jindong Gu , Yalin Wang

While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation behaviors in real time and proactively intervening before…

Computation and Language · Computer Science 2026-01-16 Yutao Mou , Zhangchi Xue , Lijun Li , Peiyang Liu , Shikun Zhang , Wei Ye , Jing Shao

The ongoing intense discussion on rising LLM usage in the scientific peer-review process has recently been mingled by reports of authors using hidden prompt injections to manipulate review scores. Since the existence of such "attacks" -…

Machine Learning · Computer Science 2025-09-26 Janis Keuper

The Large Language Models (LLMs) are poised to offer efficient and intelligent services for future mobile communication networks, owing to their exceptional capabilities in language comprehension and generation. However, the extremely high…

Cryptography and Security · Computer Science 2023-09-07 Haomiao Yang , Kunlan Xiang , Mengyu Ge , Hongwei Li , Rongxing Lu , Shui Yu

Agents powered by large language models (LLMs) have demonstrated strong capabilities in a wide range of complex, real-world applications. However, LLM agents with a compromised memory bank may easily produce harmful outputs when the past…

Machine Learning · Computer Science 2026-02-16 Shen Dong , Shaochen Xu , Pengfei He , Yige Li , Jiliang Tang , Tianming Liu , Hui Liu , Zhen Xiang

As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful behaviors from LLMs, poses an ever increasing risk. Prompt injection attacks can cause LLMs to…

Cryptography and Security · Computer Science 2025-10-24 Isaac Wu , Michael Maslowski

LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong tools and enabling malicious actions. Most existing attacks…

Cryptography and Security · Computer Science 2026-05-27 Xuanye Zhang , Yongsen Zheng , Zhuqin Xu , Kaiyu Zhou , Bowen Shen , Haoran Ou , Tianwei Zhang , Kwok-Yan Lam

Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we investigate the potential for hidden…

Cryptography and Security · Computer Science 2026-03-31 Matteo Gioele Collu , Umberto Salviati , Roberto Confalonieri , Mauro Conti , Giovanni Apruzzese

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

The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solving and autonomous negotiation. However, the security…

Computation and Language · Computer Science 2024-07-24 Tianjie Ju , Yiting Wang , Xinbei Ma , Pengzhou Cheng , Haodong Zhao , Yulong Wang , Lifeng Liu , Jian Xie , Zhuosheng Zhang , Gongshen Liu

As Large Language Models (LLMs) gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are…

Cryptography and Security · Computer Science 2025-10-20 Issam Seddik , Sami Souihi , Mohamed Tamaazousti , Sara Tucci Piergiovanni

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…

Cryptography and Security · Computer Science 2026-02-26 David Schmotz , Luca Beurer-Kellner , Sahar Abdelnabi , Maksym Andriushchenko

Reinforcement Learning (RL) is widely used in tasks where agents interact with an environment to maximize rewards. Building on this foundation, Safe Reinforcement Learning (Safe RL) incorporates a cost metric alongside the reward metric,…

Machine Learning · Computer Science 2025-07-02 Weiran Guo , Guanjun Liu , Ziyuan Zhou , Ling Wang

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…

Multiagent Systems · Computer Science 2026-04-21 Nokimul Hasan Arif , Qian Lou , Mengxin Zheng