# CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering

arXiv: https://arxiv.org/abs/2609.36570 · HTML: https://mlsanity.com/paper/2609.36570/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 49 of its 64 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)
- Mechanistic interpretability / [Steering and probing for LLM safety](https://mlsanity.com/mechinterp/steering-and-probing-for-llm-safety/)

## Builds on (most cited first, 30 of 49)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Improving Alignment and Robustness with Circuit Breakers](https://mlsanity.com/paper/2406.04313/) (2024)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [SecAlign: Defending Against Prompt Injection with Preference Optimization](https://mlsanity.com/paper/2410.05451/) (2024)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks](https://mlsanity.com/paper/2504.11358/) (2025)
- [Progent: Securing AI Agents with Privilege Control](https://mlsanity.com/paper/2504.11703/) (2025)
- [The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections](https://mlsanity.com/paper/2510.09023/) (2025)
- [The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence](https://mlsanity.com/paper/2502.17420/) (2025)
- [Jatmo: Prompt Injection Defense by Task-Specific Finetuning](https://mlsanity.com/paper/2312.17673/) (2023)
- [Attention Tracker: Detecting Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2411.00348/) (2024)
- [Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?](https://mlsanity.com/paper/2403.06833/) (2024)
- [Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching](https://mlsanity.com/paper/2311.17030/) (2023)
- [MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents](https://mlsanity.com/paper/2502.05174/) (2025)
- [Design Patterns for Securing LLM Agents against Prompt Injections](https://mlsanity.com/paper/2506.08837/) (2025)
- [Get my drift? Catching LLM Task Drift with Activation Deltas](https://mlsanity.com/paper/2406.00799/) (2024)
- [Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy](https://mlsanity.com/paper/2410.09102/) (2024)

## Abstract (arXiv)

Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that suppresses this behavior inside the model. Per model, a five-step recipe fits a residual-stream direction from paired episodes differing only in whether an embedded instruction is followed, and retains it only if it passes pre-specified causal and capability gates. At deployment, the direction is subtracted from every tool-result token during prefill. The edit is always on--there is no detection decision to evade--and requires no fine-tuning, auxiliary model, or added tokens, only white-box serving and tool-result span boundaries. Across five open-weights models (8B-106B, five vendor lineages), held-out attack success falls from 0.21-1.00 undefended to 0.00-0.17 defended, and AgentDojo compromise rate from 0.10-0.49 to 0.006-0.079, at 93-100% typography-normalized benign utility, with larger task-dependent costs when reasoning over steered content. A benchmark-level adaptive attacker reaching 0.67-0.73 undefended is held to roughly a quarter of that on the two most deeply evaluated models. Among the defenses we measured on capable models, those achieving lower compromise rates either lost 22-89% of benign utility or fine-tuned the served weights. White-box gradient attacks through the deployed vector compromise at most 2 of 52 episodes, and none of 2,052 replayed human red-team attacks succeeds. CounterSteer largely neutralizes instructional takeover: a black-box framing search cracks 3 of 18 development samples. Parameter manipulation--attacker-chosen arguments in otherwise legitimate calls--is only partially resisted (13 of 18); the decision becomes linearly readable at argument emission but not at the examined pre-generation sites, and is not removed by the tested prefill- or decode-time steering, motivating argument-provenance controls.