# Robust Context-Aware Detection of Malicious Instructions in Text

arXiv: https://arxiv.org/abs/2608.05430 · HTML: https://mlsanity.com/paper/2608.05430/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Placed in

- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 28 of 28)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Provable defenses against adversarial examples via the convex outer adversarial polytope](https://mlsanity.com/paper/1711.00851/) (2017)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://mlsanity.com/paper/1605.07725/) (2016)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [FreeLB: Enhanced Adversarial Training for Natural Language Understanding](https://mlsanity.com/paper/1909.11764/) (2019)
- [Progent: Securing AI Agents with Privilege Control](https://mlsanity.com/paper/2504.11703/) (2025)
- [IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems](https://mlsanity.com/paper/2403.04960/) (2024)
- [The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections](https://mlsanity.com/paper/2510.09023/) (2025)
- [Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents](https://mlsanity.com/paper/2503.00061/) (2025)
- [The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents](https://mlsanity.com/paper/2412.16682/) (2024)
- [System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective](https://mlsanity.com/paper/2409.19091/) (2024)
- [Attention Tracker: Detecting Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2411.00348/) (2024)
- [MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents](https://mlsanity.com/paper/2502.05174/) (2025)
- [Defending Against Physically Realizable Attacks on Image Classification](https://mlsanity.com/paper/1909.09552/) (2019)
- [DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents](https://mlsanity.com/paper/2506.12104/) (2025)
- [AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?](https://mlsanity.com/paper/2602.03117/) (2026)
- [Defending against Indirect Prompt Injection by Instruction Detection](https://mlsanity.com/paper/2505.06311/) (2025)
- [Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Features](https://mlsanity.com/paper/1708.08327/) (2017)
- [AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents](https://mlsanity.com/paper/2606.15057/) (2026)

## Built on by (most cited first, 1 of 1)

- [ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection](https://mlsanity.com/paper/2608.27496/) (2026)

## Abstract (arXiv)

The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete increasingly complex tasks. Therein, however, also lies their vulnerability to attacks which embed malicious instructions in text, common variants of which are known as indirect prompt injection (IPI). A fundamental task in addressing this vulnerability is successful segmentation of a given text into benign and malicious sentences (if any). While a number of approaches for this task have been proposed, no detector combines query-relative detection at the segment level, and none are hardened against adaptive evasion attacks realizable in agentic executions. We address the former limitation by developing an approach for malicious sentence classification that is both context- and query-aware. Next, to harden the resulting classifier against evasion, we present two adversarial training methods. The first is directly adapted feature-space adversarial training (AT) in which evasions are approximated using projected-gradient-based optimization in the embedding space. The second simulates realizable evasion attacks in the AT loop through LLM-based paraphrasing. Crucially, we parametrize both AT variants to facilitate a smooth tradeoff between utility and attack robustness. In extensive experiments using indirect prompt injection benchmarks we show that the proposed approach outperforms state-of-the-art IPI defense baselines under static attacks, while in the case of adaptive attacks, our AT variants provide significantly higher utility, lower attack success rate, and often both. Finally, we show that the best AT parameters can depend intimately on the particular application domain. Consequently, domain-dependent tuning of malicious text detectors is likely necessary in practice. Our code is publicly available at https://github.com/tavia-liu/CAD.