With the widespread adoption of Large Language Models (LLMs), prompt injection attacks have emerged as a significant security threat. Existing defense mechanisms often face critical trade-offs between effectiveness and generalizability. This highlights the urgent need for efficient prompt injection detection methods that are applicable across a wide range of LLMs. To address this challenge, we propose DMPI-PMHFE, a dual-channel feature fusion detection framework. It integrates a pretrained language model with heuristic feature engineering to detect prompt injection attacks. Specifically, the framework employs DeBERTa-v3-base as a feature extractor to transform input text into semantic vectors enriched with contextual information. In parallel, we design heuristic rules based on known attack patterns to extract explicit structural features commonly observed in attacks. Features from both channels are subsequently fused and passed through a fully connected neural network to produce the final prediction. This dual-channel approach mitigates the limitations of relying only on DeBERTa to extract features. Experimental results on diverse benchmark datasets demonstrate that DMPI-PMHFE outperforms existing methods in terms of accuracy, recall, and F1-score. Furthermore, when deployed actually, it significantly reduces attack success rates across mainstream LLMs, including GLM-4, LLaMA 3, Qwen 2.5, and GPT-4o.
Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Models
Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）；Shenyang Aerospace University（沈阳航空航天大学）；ZGC LAB, Beijing,China（北京ZGC实验室）；Institute for Network Sciences and Cyberspace, Tsinghua University（清华大学网络科学与网络空间研究院）
SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；National Astronomical Observatories, Chinese Academy of Sciences（中国科学院国家天文台）
Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters
State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机科学学院，北京大学）；WeChat AI, Tencent Inc., China（腾讯公司，中国）；The University of Hong Kong（香港大学）
Heuristics and Biases in AI Decision-Making: Implications for Responsible AGI
Golisano Institute for Sustainability Rochester Institute of Technology Rochester, The United States；Information Sciences \& Technology, CEHC University at Albany, SUNY Albany, The United States
Few-Shot Learning for Mental Disorder Detection: A Continuous Multi-Prompt Engineering Approach with Medical Knowledge Injection
Hefei University of Technology（合肥工业大学）；Iowa State University（爱荷华州立大学）；University of Delaware（特拉华大学）；University of Rhode Island（罗德岛大学）；University of Arizona（亚利桑那大学）
PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration
University of Queensland（昆士兰大学）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；Provable Responsible AI and Data Analytics (PRADA) Lab（可证责任AI与数据分析师实验室）；King Abdullah University of Science and Technology (KAUST)（国王 Abdullah 科学与技术大学）
Beyond Demonstrations: Dynamic Vector Construction from Latent Representations
National Key Laboratory for Multimedia Information Processing, Peking University（国家多媒体信息处理重点实验室，北京大学）；MOE Key Laboratory of Computational Linguistics, Peking University（教育部计算语言学重点实验室，北京大学）；School of Software and Microelectronics, Peking University（软件与微电子学院，北京大学）；School of Computer Science, Peking University（计算机科学学院，北京大学）
One Size Fits None: Heuristic Collapse in LLM Investment Advice
Computer Science and Artificial Intelligence Laboratory（计算机科学与人工智能实验室）；Massachusetts Institute of Technology（麻省理工学院）；Sloan School of Management（斯隆管理学院）
Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
State Key Laboratory of Intelligent Game（智能游戏国家重点实验室）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Role-aware Heuristic Episodic Attention for Conversational LLMs
National Key Laboratory of Parallel and Distributed Computing（平行与分布式计算国家重点实验室）；College of Computer Science and Technology（计算机科学与技术学院）；National University of Defense Technology（国防科学技术大学）
Deep Expert Injection for Anchoring Retinal VLMs with Domain-Specific Knowledge
Beijing Institute of Technology, Beijing, China（北京理工大学）；National University of Singapore, Singapore（新加坡国立大学）；Tsinghua University, Beijing, China（清华大学）；The Hong Kong Polytechnic University, Hong Kong（香港理工大学）
REMoH: A Reflective Evolution of Multi-objective Heuristics approach via Large Language Models
Vicomtech Foundation, Basque Research and Technology Alliance (BRTA)（维克姆技基金会、巴斯克研究与技术联盟（BRTA））；Department of Computer Sciences and Artificial Intelligence, University of the Basque Country (UPV/EHU)（巴斯克国家大学（UPV/EHU）计算机科学与人工智能系）；School of Applied Sciences and Engineering, Universidad EAFIT（埃法伊特大学应用科学与工程学院）；HiTZ Basque Center for Language Technology, University of the Basque Country (UPV/EHU)（巴斯克国家大学（UPV/EHU）HiTZ巴斯克语言技术中心）
Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering
School of Information Science and Technology, Hangzhou Normal University（杭州师范大学信息科学与技术学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；School of Computer Science and Technology, Hangzhou Dianzi University（杭州电子科技大学计算机科学与技术学院）
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University（航空信息安全与可信计算重点实验室、教育部、网络安全科学与工程学院、武汉大学）；Department of Computer Science and Engineering, University at Buffalo, SUNY（计算机科学与工程系、布法罗大学、纽约州立大学）；Department of Computer Science, College of Information Science and Technology, Jinan University（计算机科学系、信息科学与技术学院、济南大学）；College of Cyber Security, Jinan University（网络安全学院、济南大学）
Defenses Against Prompt Attacks Learn Surface Heuristics
University of Southern California（南加州大学）；University of California, Berkeley（加州大学伯克利分校）；Washington University in St. Louis（圣路易斯华盛顿大学）；Amazon（亚马逊公司）；Johns Hopkins University（约翰霍普金斯大学）
FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
UW-Madison（威斯康星大学麦迪逊分校）；Huazhong University of Science and Technology（华中科技大学）；University of Rochester（罗切斯特大学）；NVIDIA（英伟达公司）；Cornell University（康奈尔大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；UC-Davis（加州大学戴维斯分校）
