Image de couverture de livre

Prompt Inject Detection with Generative Explanation as an Investigative Tool

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pan, Jonathan, Wong, Swee Liang, Yuan, Yidi, Chia, Xin Wei
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Enhancing Reasoning Capacity of SLM using Cognitive Enhancement
par: Pan, Jonathan, et autres
Publié: (2024)

Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States
par: Chia, Xin Wei, et autres
Publié: (2025)

Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs
par: Pallakonda, Bhanu, et autres
Publié: (2026)

LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
par: Abdelnabi, Sahar, et autres
Publié: (2025)

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
par: Wang, Che, et autres
Publié: (2026)

AiRacleX: Automated Detection of Price Oracle Manipulations via LLM-Driven Knowledge Mining and Prompt Generation
par: Gao, Bo, et autres
Publié: (2025)

Injecting Bias into Text Classification Models using Backdoor Attacks
par: Yavuz, A. Dilara, et autres
Publié: (2024)

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
par: Zou, Wei, et autres
Publié: (2026)

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
par: Zhao, Wei, et autres
Publié: (2026)

Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
par: Liu, Fazhong, et autres
Publié: (2026)

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
par: Yan, Shenao, et autres
Publié: (2024)

Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection
par: Shokouhinejad, Hossein, et autres
Publié: (2026)

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
par: Wang, Haowei, et autres
Publié: (2025)

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection
par: Chia-Pei, et autres
Publié: (2026)

Optimization-based Prompt Injection Attack to LLM-as-a-Judge
par: Shi, Jiawen, et autres
Publié: (2024)

VADER: A Human-Evaluated Benchmark for Vulnerability Assessment, Detection, Explanation, and Remediation
par: Liu, Ethan TS., et autres
Publié: (2025)

ToolTweak: An Attack on Tool Selection in LLM-based Agents
par: Sneh, Jonathan, et autres
Publié: (2025)

Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
par: Uppala, Rohith
Publié: (2026)

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models
par: Liu, Pang, et autres
Publié: (2026)

Prompt and Circumstances: Evaluating the Efficacy of Human Prompt Inference in AI-Generated Art
par: Trinh, Khoi, et autres
Publié: (2026)

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
par: Chen, Zhuowei, et autres
Publié: (2025)

Defending against Indirect Prompt Injection by Instruction Detection
par: Wen, Tongyu, et autres
Publié: (2025)

Automating Security Audit Using Large Language Model based Agent: An Exploration Experiment
par: Chin, Jia Hui, et autres
Publié: (2025)

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
par: Ge, Huaizhi, et autres
Publié: (2024)

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
par: Maloyan, Narek, et autres
Publié: (2026)

PromptArmor: Simple yet Effective Prompt Injection Defenses
par: Shi, Tianneng, et autres
Publié: (2025)

On the Consistency of GNN Explanations for Malware Detection
par: Shokouhinejad, Hossein, et autres
Publié: (2025)

SLIFER: Investigating Performance and Robustness of Malware Detection Pipelines
par: Ponte, Andrea, et autres
Publié: (2024)

DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks
par: Liu, Yupei, et autres
Publié: (2025)

Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
par: Crawford, Brian, et autres
Publié: (2026)

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection
par: Zhang, Ivan
Publié: (2025)

SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
par: Du, Mengyao, et autres
Publié: (2026)

Extending XReason: Formal Explanations for Adversarial Detection
par: Jemaa, Amira, et autres
Publié: (2024)

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
par: Wang, Zhaoqi, et autres
Publié: (2025)

Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
par: Shan, Shawn, et autres
Publié: (2023)

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
par: An, Shengwei, et autres
Publié: (2023)

PromptLocate: Localizing Prompt Injection Attacks
par: Jia, Yuqi, et autres
Publié: (2025)

PromptKeeper: Safeguarding System Prompts for LLMs
par: Jiang, Zhifeng, et autres
Publié: (2024)

ChatGPT's Potential in Cryptography Misuse Detection: A Comparative Analysis with Static Analysis Tools
par: Firouzi, Ehsan, et autres
Publié: (2024)

OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Prompting
par: Cheng, Wenrui, et autres
Publié: (2025)