paper-with-me

홈 › Papers

Trust No AI: Prompt Injection Along The CIA Security Triad

2024-12-08 · Johann Rehberger

The CIA security triad - Confidentiality, Integrity, and Availability - is a cornerstone of data and cybersecurity. With the emergence of large language model (LLM) applications, a new class of threat, known as prompt injection, was first identified in 2022. Since then, numerous real-world vulnerabilities and exploits have been documented in production LLM systems, including those from leading vendors like OpenAI, Microsoft, Anthropic and Google. This paper compiles real-world exploits and proof-of concept examples, based on the research conducted and publicly documented by the author, demonstrating how prompt injection undermines the CIA triad and poses ongoing risks to cybersecurity and AI systems at large.

📄 PDF Abstract BibTeX arXiv:2412.06090

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models

2023-11-19 · Erik Derner, Kristina Batistič, Jan Zahálka, Robert Babuška

As large language models (LLMs) permeate more and more applications, an assessment of their associated security risks becomes increasingly necessary. The potential for exploitation by malicious actors, ranging from disin…

Defeating Prompt Injections by Design

2025-03-24 · Edoardo Debenedetti, Ilia Shumailov, Tianqi Fan, Jamie Hayes 외

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this …

Prompt Fencing: A Cryptographic Approach to Establishing Security Boundaries in Large Language Model Prompts

2025-11-24 · Steven Peh arxiv

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that appl…

Agent Data Injection Attacks are Realistic Threats to AI Agents

2026-07-06 · Woohyuk Choi, Juhee Kim, Taehyun Kang, Jihyeon Jeong 외 arxiv

AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security has primarily focused on indirect prompt injection (IPI). Its most well-…

Assessing Prompt Injection Risks in 200+ Custom GPTs

2023-11-20 · Jiahao Yu, Yuhang Wu, Dong Shu, Mingyu Jin 외

In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications. The new feature - customization of ChatGPT models by users to cater to specific needs has opened new fro…