Image de couverture de livre

ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chang, Hwan, Jun, Yonghyun, Lee, Hwanhee
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis
par: Jun, Yonghyun, et autres
Publié: (2024)

Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering
par: Chang, Hwan, et autres
Publié: (2025)

Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation
par: Jun, Yonghyun, et autres
Publié: (2025)

Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning
par: Chang, Hwan, et autres
Publié: (2025)

Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models
par: Jang, Haeun, et autres
Publié: (2026)

WebInject: Prompt Injection Attack to Web Agents
par: Wang, Xilong, et autres
Publié: (2025)

Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval
par: Baek, Ingeol, et autres
Publié: (2024)

Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization
par: Yang, Joonho, et autres
Publié: (2025)

Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents
par: Park, Jihyeong, et autres
Publié: (2026)

MQM-Chat: Multidimensional Quality Metrics for Chat Translation
par: Li, Yunmeng, et autres
Publié: (2024)

MathChat: Converse to Tackle Challenging Math Problems with LLM Agents
par: Wu, Yiran, et autres
Publié: (2023)

VideoChat: Chat-Centric Video Understanding
par: Li, KunChang, et autres
Publié: (2023)

ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT
par: Wei, Xiang, et autres
Publié: (2023)

On Prompt Sensitivity of ChatGPT in Affective Computing
par: Amin, Mostafa M., et autres
Publié: (2024)

FuseChat: Knowledge Fusion of Chat Models
par: Wan, Fanqi, et autres
Publié: (2024)

AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior
par: Gu, Zhouhong, et autres
Publié: (2024)

ChatUIE: Exploring Chat-based Unified Information Extraction using Large Language Models
par: Xu, Jun, et autres
Publié: (2024)

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
par: Kong, Huanjun, et autres
Publié: (2024)

A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1
par: Wang, Jun
Publié: (2025)

Investigating Language Preference of Multilingual RAG Systems
par: Park, Jeonghyun, et autres
Publié: (2025)

Conversational Query Reformulation with the Guidance of Retrieved Documents
par: Park, Jeonghyun, et autres
Publié: (2024)

AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need
par: Gu, Zhouhong, et autres
Publié: (2025)

ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Structured Knowledge and Reasoning
par: Fan, E, et autres
Publié: (2025)

ChatShop: Interactive Information Seeking with Language Agents
par: Chen, Sanxing, et autres
Publié: (2024)

DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation
par: Wang, Jiapeng, et autres
Publié: (2024)

APT-Pipe: A Prompt-Tuning Tool for Social Data Annotation using ChatGPT
par: Zhu, Yiming, et autres
Publié: (2024)

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
par: Wang, Peiran, et autres
Publié: (2026)

ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents
par: Li, Zhigen, et autres
Publié: (2024)

WildChat: 1M ChatGPT Interaction Logs in the Wild
par: Zhao, Wenting, et autres
Publié: (2024)

Prompting ChatGPT for Translation: A Comparative Analysis of Translation Brief and Persona Prompts
par: He, Sui
Publié: (2024)

Optimizing Machine Translation through Prompt Engineering: An Investigation into ChatGPT's Customizability
par: Yamada, Masaru
Publié: (2023)

Selective Demonstration Retrieval for Improved Implicit Hate Speech Detection
par: Kim, Yumin, et autres
Publié: (2025)

Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities
par: Fuchs, Ronja, et autres
Publié: (2026)

Guiding ChatGPT to Generate Salient Domain Summaries
par: Gao, Jun, et autres
Publié: (2024)

ChatDev: Communicative Agents for Software Development
par: Qian, Chen, et autres
Publié: (2023)

Assessing the Impact of Prompting Methods on ChatGPT's Mathematical Capabilities
par: Chen, Yuhao, et autres
Publié: (2023)

Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
par: Liu, Yi, et autres
Publié: (2023)

ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time
par: Tu, Shangqing, et autres
Publié: (2023)

Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text
par: Yang, Lingyi, et autres
Publié: (2023)

Chat Bankman-Fried: an Exploration of LLM Alignment in Finance
par: Biancotti, Claudia, et autres
Publié: (2024)