Prompt injection has emerged as a critical vulnerability in large language model (LLM) deployments, yet existing research is heavily weighted toward defenses. The attack side -- specifically, which injection strategies are most effective and why -- remains insufficiently studied.We address this gap with AttackEval, a systematic empirical study of prompt injection attack effectiveness. We construct a taxonomy of ten attack categories organized into three parent groups (Syntactic, Contextual, and Semantic/Social), populate each category with 25 carefully crafted prompts (250 total), and evaluate them against a simulated production victim system under four progressively stronger defense tiers. Experiments reveal several non-obvious findings: (1) Obfuscation (OBF) achieves the highest single-attack success rate (ASR = 0.76) against even intent-aware defenses, because it defeats both keyword matching and semantic similarity checks simultaneously; (2) Semantic/Social attacks - Emotional Manipulation (EM) and Reward Framing (RF) - maintain high ASR (0.44-0.48) against intent-aware defenses due to their natural language surface, which evades structural anomaly detection; (3) Composite attacks combining two complementary strategies dramatically boost ASR, with the OBF + EM pair reaching 97.6%; (4) Stealth correlates positively with residual ASR against semantic defenses (r = 0.71), implying that future defenses must jointly optimize for both structural and behavioral signals. Our findings identify concrete blind spots in current defenses and provide actionable guidance for designing more robust LLM safety systems.
Misleading Large Language Models used (or misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks
University of Padua(帕多瓦大学);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会);Örebro University(厄勒布鲁大学);Reykjavik University(雷克雅未克大学);University of Liechtenstein(列支敦士登大学)
The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism
Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev(本·古里安大学软件与信息系统工程系);School of Electrical and Computer Engineering, Tel Aviv University(特拉维夫大学电气与计算机工程学院);Harvard Kennedy School, Harvard University, and Munk School, University of Toronto(哈佛大学哈佛肯尼迪学校及多伦多大学穆克学校)
What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);AI Sec Lab, Beijing Chaitin Technology Co.,Ltd(北京柴坦科技有限公司AI安全实验室)
UC Berkeley(加州大学伯克利分校);UC Santa Barbara(加州大学圣巴巴拉分校);Duke University(杜克大学);National University of Singapore(新加坡国立大学);King Abdulaziz City for Science and Technology(国王阿卜杜勒阿齐兹城市科学技术学院);University of Washington(华盛顿大学)
When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems
School of Informatics, Computing, and Cyber Systems, Northern Arizona University(北亚利桑那大学信息学、计算与网络安全学院);Department of Software Science, Tallinn University of Technology(塔林理工大学软件科学系)
Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI)(德国人工智能研究中心);Centre for European Research in Trusted AI (CERTAIN)(欧洲可信人工智能研究中心);sequire technology GmbH(sequire技术有限公司)