# Gandalf the Red: Adaptive Security for LLMs

arXiv: https://arxiv.org/abs/2501.07927 · HTML: https://mlsanity.com/paper/2501.07927/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 68 references that are in the map.
- First posted on arXiv 14 Jan 2025.

## Builds on (most cited first, 30 of 30)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Low-Resource Languages Jailbreak GPT-4](https://mlsanity.com/paper/2310.02446/) (2023)
- [Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks](https://mlsanity.com/paper/2302.05733/) (2023)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [Certifying LLM Safety against Adversarial Prompting](https://mlsanity.com/paper/2309.02705/) (2023)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2401.17263/) (2024)
- [Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game](https://mlsanity.com/paper/2311.01011/) (2023)
- [Automatic and Universal Prompt Injection Attacks against Large Language Models](https://mlsanity.com/paper/2403.04957/) (2024)
- [Jatmo: Prompt Injection Defense by Task-Specific Finetuning](https://mlsanity.com/paper/2312.17673/) (2023)
- [Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks](https://mlsanity.com/paper/2403.03792/) (2024)
- [Attack Prompt Generation for Red Teaming and Defending Large Language Models](https://mlsanity.com/paper/2310.12505/) (2023)
- [Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)](https://mlsanity.com/paper/2407.14937/) (2024)
- [An Early Categorization of Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2402.00898/) (2024)
- [Embedding-based classifiers can detect prompt injection attacks](https://mlsanity.com/paper/2410.22284/) (2024)
- [Lightweight Safety Classification Using Pruned Language Models](https://mlsanity.com/paper/2412.13435/) (2024)

## Built on by (most cited first, 7 of 7)

- [The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections](https://mlsanity.com/paper/2510.09023/) (2025)
- [Activated LoRA: Fine-tuned LLMs for Intrinsics](https://mlsanity.com/paper/2504.12397/) (2025)
- [Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents](https://mlsanity.com/paper/2510.22620/) (2025)
- [Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models](https://mlsanity.com/paper/2506.13726/) (2025)
- [K2-V2: A 360-Open, Reasoning-Enhanced LLM](https://mlsanity.com/paper/2512.06201/) (2025)
- [RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models](https://mlsanity.com/paper/2601.03699/) (2026)
- [Conditioned Activation Transport for T2I Safety Steering](https://mlsanity.com/paper/2603.03163/) (2026)

## Abstract (arXiv)

Current evaluations of defenses against prompt attacks in large language model (LLM) applications often overlook two critical factors: the dynamic nature of adversarial behavior and the usability penalties imposed on legitimate users by restrictive defenses. We propose D-SEC (Dynamic Security Utility Threat Model), which explicitly separates attackers from legitimate users, models multi-step interactions, and expresses the security-utility in an optimizable form. We further address the shortcomings in existing evaluations by introducing Gandalf, a crowd-sourced, gamified red-teaming platform designed to generate realistic, adaptive attack. Using Gandalf, we collect and release a dataset of 279k prompt attacks. Complemented by benign user data, our analysis reveals the interplay between security and utility, showing that defenses integrated in the LLM (e.g., system prompts) can degrade usability even without blocking requests. We demonstrate that restricted application domains, defense-in-depth, and adaptive defenses are effective strategies for building secure and useful LLM applications.