English
Related papers

Related papers: FlowSteer: Prompt-Only Workflow Steering Exposes P…

200 papers

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Artificial Intelligence · Computer Science 2026-05-13 Xinyi Zeng , Xue Yang , Jingyuan Zhang , Huanqian Yan , Xiang Chen , Kaiwen Wei , Hankun Kang , Yu Tian

Large Reasoning Models (LRMs) excel at complex reasoning tasks, but their efficiency is often hampered by overly verbose outputs. Prior steering methods attempt to address this issue by applying a single, global vector to hidden…

Machine Learning · Computer Science 2026-02-06 Yawei Li , Benjamin Bergner , Yinghan Zhao , Vihang Prakash Patil , Bei Chen , Cheng Wang

Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working memory through their context window, which stores interaction…

Cryptography and Security · Computer Science 2026-02-10 Ruoyao Wen , Hao Li , Chaowei Xiao , Ning Zhang

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Cryptography and Security · Computer Science 2026-05-12 Matteo Lupinacci , Francesco Aurelio Pironti , Francesco Blefari , Francesco Romeo , Luigi Arena , Angelo Furfaro

As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an…

Machine Learning · Computer Science 2026-02-10 Leheng Sheng , Changshuo Shen , Weixiang Zhao , Junfeng Fang , Xiaohao Liu , Zhenkai Liang , Xiang Wang , An Zhang , Tat-Seng Chua

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Cryptography and Security · Computer Science 2025-05-30 Jinchuan Zhang , Lu Yin , Yan Zhou , Songlin Hu

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

As LLM-based Multi-Agent Systems (MAS) are increasingly deployed for complex tasks, ensuring their reliability has become a pressing challenge. Since MAS coordinate through unstructured natural language rather than rigid protocols, they are…

Software Engineering · Computer Science 2026-02-24 Jin Jia , Zhiling Deng , Zhuangbin Chen , Yingqi Wang , Zibin Zheng

LLM workflows, which coordinate structured calls to individual LLMs/agents to achieve a particular goal, offer a promising path towards building powerful AI systems that can tackle diverse tasks. However, existing approaches for building…

Computation and Language · Computer Science 2026-05-04 Hongyeon Yu , Young-Bum Kim , Yoon Kim

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

Cryptography and Security · Computer Science 2024-10-23 Xiaohan Fu , Shuheng Li , Zihan Wang , Yihao Liu , Rajesh K. Gupta , Taylor Berg-Kirkpatrick , Earlence Fernandes

Prompt leakage poses a compelling security and privacy threat in LLM applications. Leakage of system prompts may compromise intellectual property, and act as adversarial reconnaissance for an attacker. A systematic evaluation of prompt…

Cryptography and Security · Computer Science 2024-07-30 Divyansh Agarwal , Alexander R. Fabbri , Ben Risher , Philippe Laban , Shafiq Joty , Chien-Sheng Wu

Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…

Multiagent Systems · Computer Science 2026-05-12 Tianxiao Li , Yixing Ma , Haiquan Wen , Zhenglin Huang , Qianyu Zhou , Zeyu Fu , Guangliang Cheng

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Machine Learning · Computer Science 2025-06-06 Shaona Ghosh , Amrita Bhattacharjee , Yftah Ziser , Christopher Parisien

This paper presents a defense framework for enhancing the safety of large language model (LLM) empowered multi-agent systems (MAS) in safety-critical domains such as aerospace. We apply randomized smoothing, a statistical robustness…

Artificial Intelligence · Computer Science 2025-07-08 Jinwei Hu , Yi Dong , Zhengtao Ding , Xiaowei Huang

LLM-based multi-agent systems (LLM-MAS) have become a promising paradigm for solving complex tasks through role specialization, tool use, memory, and collaborative reasoning. However, these interactions create new security risks that…

Machine Learning · Computer Science 2026-05-19 Bingyu Yan , Xiaoming Zhang , Jinyu Hou , Chaozhuo Li , Ziyi Zhou , Xiaozhe Zhang , Litian Zhang

As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has examined the safety and misuse risks associated with agents.…

Artificial Intelligence · Computer Science 2026-02-26 Akshat Naik , Jay Culligan , Yarin Gal , Philip Torr , Rahaf Aljundi , Alasdair Paren , Adel Bibi

Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…

Cryptography and Security · Computer Science 2026-04-15 Yulin Chen , Tri Cao , Haoran Li , Yue Liu , Yibo Li , Yufei He , Le Minh Khoi , Yangqiu Song , Shuicheng Yan , Bryan Hooi

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

Artificial Intelligence · Computer Science 2026-05-05 Sheldon Yu , Yingcheng Sun , Hanqing Guo , Julian McAuley , Qianqian Tong

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, and LLM-based agents further extend these abilities to various practical workflows. While recent progress shows that multi-agent systems (MAS) can…

Computation and Language · Computer Science 2025-10-10 Zheyuan Zhang , Lin Ge , Hongjiang Li , Weicheng Zhu , Chuxu Zhang , Yanfang Ye

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Cryptography and Security · Computer Science 2026-05-05 Lingxi Zhang , Guangtao Zheng , Hanjie Chen