# A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems

arXiv: https://arxiv.org/abs/2402.18649 · HTML: https://mlsanity.com/paper/2402.18649/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 27 of 27)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [Mathematical Capabilities of ChatGPT](https://mlsanity.com/paper/2301.13867/) (2023)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks](https://mlsanity.com/paper/2310.10844/) (2023)
- [Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference](https://mlsanity.com/paper/1906.11798/) (2019)
- [Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game](https://mlsanity.com/paper/2311.01011/) (2023)
- [From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy](https://mlsanity.com/paper/2307.00691/) (2023)
- [Jatmo: Prompt Injection Defense by Task-Specific Finetuning](https://mlsanity.com/paper/2312.17673/) (2023)
- [Examining Zero-Shot Vulnerability Repair with Large Language Models](https://mlsanity.com/paper/2112.02125/) (2021)
- [ChatGPT is not all you need. A State of the Art Review of large Generative AI models](https://mlsanity.com/paper/2301.04655/) (2023)
- [From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?](https://mlsanity.com/paper/2308.01990/) (2023)
- [Assessing Prompt Injection Risks in 200+ Custom GPTs](https://mlsanity.com/paper/2311.11538/) (2023)
- [Unveiling Security, Privacy, and Ethical Concerns of ChatGPT](https://mlsanity.com/paper/2307.14192/) (2023)
- [LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins](https://mlsanity.com/paper/2309.10254/) (2023)
- [Evaluation of ChatGPT Model for Vulnerability Detection](https://mlsanity.com/paper/2304.07232/) (2023)
- [An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)](https://mlsanity.com/paper/2302.13814/) (2023)
- [A Novel Evaluation Framework for Assessing Resilience Against Prompt Injection Attacks in Large Language Models](https://mlsanity.com/paper/2401.00991/) (2024)
- [Safeguarding Crowdsourcing Surveys from ChatGPT with Prompt Injection](https://mlsanity.com/paper/2306.08833/) (2023)
- [AI Insights into Theoretical Physics and the Swampland Program: A Journey Through the Cosmos with ChatGPT](https://mlsanity.com/paper/2301.08155/) (2023)
- [Compositional Security for Reentrant Applications](https://mlsanity.com/paper/2103.08577/) (2021)

## Built on by (most cited first, 30 of 77)

- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks](https://mlsanity.com/paper/2504.18575/) (2025)
- [Progent: Securing AI Agents with Privilege Control](https://mlsanity.com/paper/2504.11703/) (2025)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective](https://mlsanity.com/paper/2409.19091/) (2024)
- [AirGapAgent: Protecting Privacy-Conscious Conversational Agents](https://mlsanity.com/paper/2405.05175/) (2024)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents](https://mlsanity.com/paper/2503.09780/) (2025)
- [MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents](https://mlsanity.com/paper/2502.05174/) (2025)
- [When LLMs Meet Cybersecurity: A Systematic Literature Review](https://mlsanity.com/paper/2405.03644/) (2024)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework](https://mlsanity.com/paper/2410.12855/) (2024)
- [Large Language Models for UAVs: Current State and Pathways to the Future](https://mlsanity.com/paper/2405.01745/) (2024)
- [Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges](https://mlsanity.com/paper/2510.23883/) (2025)
- [Security of AI Agents](https://mlsanity.com/paper/2406.08689/) (2024)
- [SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems](https://mlsanity.com/paper/2506.07564/) (2025)
- [Prompt Leakage effect and defense strategies for multi-turn LLM interactions](https://mlsanity.com/paper/2404.16251/) (2024)
- [CodeMirage: Hallucinations in Code Generated by Large Language Models](https://mlsanity.com/paper/2408.08333/) (2024)
- [Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions](https://mlsanity.com/paper/2501.04437/) (2025)
- [AgentBound: Securing Execution Boundaries of AI Agents](https://mlsanity.com/paper/2510.21236/) (2025)
- [ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking](https://mlsanity.com/paper/2512.07086/) (2025)
- [ConfusedPilot: Confused Deputy Risks in RAG-based LLMs](https://mlsanity.com/paper/2408.04870/) (2024)
- [FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks](https://mlsanity.com/paper/2410.21492/) (2024)
- [Frontier AI's Impact on the Cybersecurity Landscape](https://mlsanity.com/paper/2504.05408/) (2025)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [A Survey on Model Extraction Attacks and Defenses for Large Language Models](https://mlsanity.com/paper/2506.22521/) (2025)
- [Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases](https://mlsanity.com/paper/2412.18295/) (2024)

## Abstract (arXiv)

Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and so on. Along with the great potential, there are also increasing concerns over the security of such probabilistic intelligent systems. However, existing studies on LLM security often focus on individual LLM, but without examining the ecosystem through the lens of LLM systems with other objects (e.g., Frontend, Webtool, Sandbox, and so on). In this paper, we systematically analyze the security of LLM systems, instead of focusing on the individual LLMs. To do so, we build on top of the information flow and formulate the security of LLM systems as constraints on the alignment of the information flow within LLM and between LLM and other objects. Based on this construction and the unique probabilistic nature of LLM, the attack surface of the LLM system can be decomposed into three key components: (1) multi-layer security analysis, (2) analysis of the existence of constraints, and (3) analysis of the robustness of these constraints. To ground this new attack surface, we propose a multi-layer and multi-step approach and apply it to the state-of-art LLM system, OpenAI GPT4. Our investigation exposes several security issues, not just within the LLM model itself but also in its integration with other components. We found that although the OpenAI GPT4 has designed numerous safety constraints to improve its safety features, these safety constraints are still vulnerable to attackers. To further demonstrate the real-world threats of our discovered vulnerabilities, we construct an end-to-end attack where an adversary can illicitly acquire the user's chat history, all without the need to manipulate the user's input or gain direct access to OpenAI GPT4. Our demo is in the link: https://fzwark.github.io/LLM-System-Attack-Demo/