# AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender

arXiv: https://arxiv.org/abs/2504.09466 · HTML: https://mlsanity.com/paper/2504.09466/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 39 of its 55 references that are in the map.
- First posted on arXiv 13 Apr 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)
- 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 39)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://mlsanity.com/paper/2304.05197/) (2023)
- [Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models](https://mlsanity.com/paper/2307.14539/) (2023)
- [A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily](https://mlsanity.com/paper/2311.08268/) (2023)
- [SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding](https://mlsanity.com/paper/2402.08983/) (2024)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Automatically Auditing Large Language Models via Discrete Optimization](https://mlsanity.com/paper/2303.04381/) (2023)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance](https://mlsanity.com/paper/2401.11206/) (2024)
- [Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories](https://mlsanity.com/paper/2406.00034/) (2024)

## Built on by (most cited first, 30 of 38)

- [LLMs Encode Harmfulness and Refusal Separately](https://mlsanity.com/paper/2507.11878/) (2025)
- [AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint](https://mlsanity.com/paper/2506.07022/) (2025)
- [When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners](https://mlsanity.com/paper/2505.15257/) (2025)
- [RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards](https://mlsanity.com/paper/2506.07736/) (2025)
- [MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering](https://mlsanity.com/paper/2510.04217/) (2025)
- [Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement](https://mlsanity.com/paper/2506.15647/) (2025)
- [SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering](https://mlsanity.com/paper/2510.17633/) (2025)
- [When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents](https://mlsanity.com/paper/2601.17887/) (2026)
- [Read the Scene, Not the Script: Outcome-Aware Safety for LLMs](https://mlsanity.com/paper/2510.04320/) (2025)
- [Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection](https://mlsanity.com/paper/2508.20766/) (2025)
- [Steering at the Source: Style Modulation Heads for Robust Persona Control](https://mlsanity.com/paper/2603.13249/) (2026)
- [Minimizing Collateral Damage in Activation Steering](https://mlsanity.com/paper/2605.01167/) (2026)
- [TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense](https://mlsanity.com/paper/2604.07727/) (2026)
- [Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence](https://mlsanity.com/paper/2604.08169/) (2026)
- [ClawLess: A Security Model of AI Agents](https://mlsanity.com/paper/2604.06284/) (2026)
- [LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety](https://mlsanity.com/paper/2604.12710/) (2026)
- [When is Your LLM Steerable?](https://mlsanity.com/paper/2606.11599/) (2026)
- [AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent](https://mlsanity.com/paper/2606.22673/) (2026)
- [Mitigating Memorization Where It Happens](https://mlsanity.com/paper/2602.08901/) (2026)
- [Test-Time Safety Alignment](https://mlsanity.com/paper/2604.26167/) (2026)
- [Low-Resource Safety Failures Are Action Failures, Not Representation Failures](https://mlsanity.com/paper/2606.01196/) (2026)
- [ShallowJail: Steering Jailbreaks against Large Language Models](https://mlsanity.com/paper/2602.07107/) (2026)
- [Hallucination as an Anomaly: Dynamic Intervention via Probabilistic Circuits](https://mlsanity.com/paper/2605.05953/) (2026)
- [Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction](https://mlsanity.com/paper/2605.18104/) (2026)
- [Safin-1: Safety from Within through Memory-Native State Evolution](https://mlsanity.com/paper/2609.00092/) (2026)
- [Why Do Large Language Models Generate Harmful Content?](https://mlsanity.com/paper/2604.11663/) (2026)
- [A Systematic Study of Training-Free Methods for Trustworthy Large Language Models](https://mlsanity.com/paper/2604.15789/) (2026)
- [Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models](https://mlsanity.com/paper/2605.00123/) (2026)
- [Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training](https://mlsanity.com/paper/2605.28467/) (2026)
- [Harnessing Textual Refusal Directions for Multimodal Safety](https://mlsanity.com/paper/2606.31876/) (2026)

## Abstract (arXiv)

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs. To address this, we propose AdaSteer, an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics. We identify two key properties: Rejection Law (R-Law), which shows that stronger steering is needed for jailbreak inputs opposing the rejection direction, and Harmfulness Law (H-Law), which differentiates adversarial and benign inputs. AdaSteer steers input representations along both the Rejection Direction (RD) and Harmfulness Direction (HD), with adaptive coefficients learned via logistic regression, ensuring robust jailbreak defense while preserving benign input handling. Experiments on LLaMA-3.1, Gemma-2, and Qwen2.5 show that AdaSteer outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility. Our results highlight the potential of interpretable model internals for real-time, flexible safety enforcement in LLMs.