v1v2 (latest)

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

5 March 2024

ArXiv (abs)PDF HTML Github (63★)

Papers citing "InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents"

50 / 135 papers shown

Title
Measuring Harmfulness of Computer-Using Agents Aaron Xuxiang Tian Ruofan Zhang J. Tang Ji Wang Tianyu Shi Jiaxin Wen ELM 100 1 0 31 Jul 2025
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition Andy Zou Maxwell Lin Eliot Krzysztof Jones Micha Nowak Mateusz Dziemian ... Nate Burnikell Yarin Gal Dan Hendrycks J. Zico Kolter Matt Fredrikson LLMAG AAML ELM 148 6 0 28 Jul 2025
PromptArmor: Simple yet Effective Prompt Injection Defenses Tianneng Shi Lingyao Li Yu Yang Yuqi Jia Will Cai ... Xuandong Zhao William Y. Wang Neil Zhenqiang Gong Wenbo Guo Dawn Song 151 27 0 21 Jul 2025
Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems Qian Xiong Yuekai Huang Ziyou Jiang Zhiyuan Chang Yujia Zheng Tianhao Li Mingyang Li 148 5 0 21 Jul 2025
TopicAttack: An Indirect Prompt Injection Attack via Topic Transition Yihao Chen Haoran Li Y. Li Yue Liu Yangqiu Song Bryan Hooi SILM AAML 199 4 0 18 Jul 2025
Evaluating LLMs on Sequential API Call Through Automated Test Generation Yuheng Huang Jiayang Song Da Song Zhenlan Ji Wenhan Wang Shuai Wang Lei Ma ELM 42 1 0 13 Jul 2025
Defending Against Prompt Injection With a Few DefensiveTokens Sizhe Chen Yizhu Wang Nicholas Carlini Chawin Sitawarin David Wagner LLMAG AAML SILM 210 12 0 10 Jul 2025
Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks Sizhe Chen Arman Zharmagambetov David Wagner Chuan Guo AAML 234 23 0 03 Jul 2025
GPT, But Backwards: Exactly Inverting Language Model Outputs Adrians Skapars Edoardo Manino Youcheng Sun Lucas C. Cordeiro 154 0 0 02 Jul 2025
DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents Hao Li Xiaogeng Liu Hung-Chun Chiu Dianqi Li Ning Zhang Chaowei Xiao AAML 283 5 0 13 Jun 2025
Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives Wei Zeng Hengshu Zhu Chuan Qin Han Wu Yihang Cheng ... Xiaowei Jin Yinuo Shen Zhenxing Wang Feimin Zhong Hui Xiong AI4TS 425 0 0 11 Jun 2025
JavelinGuard: Low-Cost Transformer Architectures for LLM Security Yash Datta Sharath Rajasekar 177 1 0 09 Jun 2025
Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components Ram Potham 219 1 0 03 Jun 2025
Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS Pengfei He Yue Xing Shen Dong Juanhui Li Zhenwei Dai ... Hui Liu Han Xu Zhen Xiang Charu C. Aggarwal Hui Liu LLMAG 406 3 0 02 Jun 2025
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Meysam Alizadeh Zeynab Samei Daria Stetsenko Fabrizio Gilardi SILM 300 7 0 01 Jun 2025
Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems Zherui Li Yan Mi Zhenhong Zhou Houcheng Jiang Guibin Zhang Kun Wang Junfeng Fang LLMAG 150 3 0 31 May 2025
RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents Jingyi Yang Shuai Shao Dongrui Liu Jing Shao 606 7 0 31 May 2025
When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Xinyue Shen Yun Shen Michael Backes Yang Zhang 179 0 0 30 May 2025
Securing AI Agents with Information-Flow Control Manuel Costa Boris Köpf Aashish Kolluri Andrew Paverd M. Russinovich Ahmed Salem Shruti Tople Lukas Wutschitz Santiago Zanella Béguelin 713 18 0 29 May 2025
LLM Agents Should Employ Security Principles Kaiyuan Zhang Zian Su Pin-Yu Chen E. Bertino Xiangyu Zhang Ninghui Li LLMAG 262 12 0 29 May 2025
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments Zeyi Liao Jaylen Jones Linxi Jiang Eric Fosler-Lussier Eric Fosler-Lussier Yu-Chuan Su Zhiqiang Lin Huan Sun ELM 411 10 0 28 May 2025
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Xueyang Zhou Weidong Wang Lin Lu Jiawen Shi Guiyao Tie Yongtian Xu Lixing Chen Pan Zhou Neil Zhenqiang Gong Lichao Sun LLMAG 452 2 0 23 May 2025
Tool Preferences in Agentic LLMs are Unreliable Kazem Faghih Wenxiao Wang Yize Cheng Siddhant Bharti Gaurang Sriramanan S. Balasubramanian Parsa Hosseini Soheil Feizi LLMAG KELM 264 0 0 23 May 2025
Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models Junjie Xiong Changjia Zhu Shuhang Lin Kai Wei Zelong Li Yao Liu Jinkui Chi 411 5 0 22 May 2025
MAPS: A Multilingual Benchmark for Global Agent Performance and Security Omer Hofman Jonathan Brokman Oren Rachmil Shamik Bose Vikas Pahuja Toshiya Shimizu Trisha Starostina Kelly Marchisio Seraphina Goldfarb-Tarrant Roman Vainshtein 224 1 0 21 May 2025
Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs Jiawen Wang Pritha Gupta Ivan Habernal Eyke Hüllermeier SILM AAML 243 6 0 20 May 2025
ToolSpectrum : Towards Personalized Tool Utilization for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Zihao Cheng Hongru Wang Zeming Liu Yuhang Guo Yuanfang Guo Yunhong Wang Haifeng Wang 307 3 0 19 May 2025
A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron? Ada Chen Yongjiang Wu Jing Zhang Shu Yang Shu Yang Jen-tse Huang Wenxuan Wang Wenxuan Wang S. Wang ELM 406 11 0 16 May 2025
WebInject: Prompt Injection Attack to Web Agents Xilong Wang John Bloch Zedian Shao Yuepeng Hu Shuyan Zhou Neil Zhenqiang Gong AAML LLMAG 439 10 0 16 May 2025
System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection Zongze Li Jiawei Guo Haipeng Cai SILM AAML 271 11 0 10 May 2025
Practical Reasoning Interruption Attacks on Reasoning Large Language Models Yu Cui Cong Zuo SILM AAML LRM 314 3 0 10 May 2025
Defending against Indirect Prompt Injection by Instruction Detection Tongyu Wen Chenglong Wang Xiyuan Yang Haoyu Tang Yueqi Xie Lingjuan Lyu Zhicheng Dou Fangzhao Wu AAML 306 5 0 08 May 2025
Safeguard-by-Development: A Privacy-Enhanced Development Paradigm for Multi-Agent Collaboration Systems Jian Cui Zichuan Li Luyi Xing Xiaojing Liao 350 1 0 07 May 2025
Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction Yuxiao Chen Haoran Li Yuan Sui Yi Liu Yufei He Yangqiu Song Xu Cheng AAML SILM 435 11 0 29 Apr 2025
CachePrune: Neural-Based Attribution Defense Against Indirect Prompt Injection Attacks Rui Wang Junda Wu Yu Xia Tong Yu Ruiyi Zhang Ryan Rossi Lina Yao Julian McAuley Julian McAuley AAML SILM 342 5 0 29 Apr 2025
ACE: A Security Architecture for LLM-Integrated App Systems Evan Li Tushin Mallick Evan Rose William K. Robertson Alina Oprea Cristina Nita-Rotaru 514 11 0 29 Apr 2025
Prompt Injection Attack to Tool Selection in LLM Agents Jiawen Shi Zenghui Yuan Guiyao Tie Pan Zhou Neil Zhenqiang Gong Lichao Sun LLMAG 397 32 0 28 Apr 2025
WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks Ivan Evtimov Arman Zharmagambetov Aaron Grattafiori Chuan Guo Kamalika Chaudhuri ELM 415 36 0 22 Apr 2025
Manipulating Multimodal Agents via Cross-Modal Prompt Injection Le Wang Zonghao Ying Tianyuan Zhang Yaning Tan Shengshan Hu Mingchuan Zhang A. Liu Xianglong Liu AAML 747 20 0 19 Apr 2025
Exploiting Fine-Grained Skip Behaviors for Micro-Video RecommendationAAAI Conference on Artificial Intelligence (AAAI), 2025 Sanghyuck Lee Sangkeun Park Jaesung Lee 233 1 0 04 Apr 2025
Emerging Cyber Attack Risks of Medical AI Agents Jianing Qiu Lin Li Jiankai Sun Hao Wei Zhe Xu K. Lam Wu Yuan AAML 341 7 0 02 Apr 2025
Towards Trustworthy GUI Agents: A Survey Yucheng Shi Wenhao Yu Wenlin Yao Wenhu Chen Ninghao Liu 261 16 0 30 Mar 2025
sudo rm -rf agentic_security Sejin Lee Jian Kim Haon Park Ashkan Yousefpour Sangyoon Yu Min Song AAML 1.1K 6 0 26 Mar 2025
CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities Yuxuan Zhu Antony Kellermann Dylan Bowman Philip Li Akul Gupta ... Avi Dhir Sudhit Rao Kaicheng Yu Twm Stone Daniel Kang LLMAG ELM 496 35 0 21 Mar 2025
Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models Chengkai Huang Junda Wu Yu Xia Zixu Yu Ruhan Wang ... Ryan Rossi Branislav Kveton Dongruo Zhou Julian McAuley Lina Yao 304 14 0 20 Mar 2025
SPADE: Structured Prompting Augmentation for Dialogue Enhancement in Machine-Generated Text Detection Haoyi Li Angela Yifei Yuan Soyeon Caren Han Christopher Leckie 283 0 0 19 Mar 2025
Multi-Agent Systems Execute Arbitrary Malicious Code Harold Triedman Rishi Jha Vitaly Shmatikov LLMAG AAML 380 18 0 15 Mar 2025
SafeArena: Evaluating the Safety of Autonomous Web Agents Ada Defne Tur Nicholas Meade Xing Han Lù Alejandra Zambrano Arkil Patel Esin Durmus Spandana Gella Karolina Stañczak Siva Reddy LLMAG ELM 359 33 0 06 Mar 2025
SpiritSight Agent: Advanced GUI Agent with One LookComputer Vision and Pattern Recognition (CVPR), 2025 Zhiyuan Huang Ziming Cheng Junting Pan Zhaohui Hou Mingjie Zhan LLMAG 392 11 0 05 Mar 2025
UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning J.N. Zhang Shuang Yang B. Li AAML LLMAG 331 6 0 28 Feb 2025