Related papers: Adaptive Probe-based Steering for Robust LLM Jailbreaking

Adaptive Probe-based Steering for Robust LLM Jailbreaking

URL: http://arxiv.org/abs/2605.20286v1
Date: Tue, 19 May 2026 06:11:04 GMT
Title: Adaptive Probe-based Steering for Robust LLM Jailbreaking
Abstract summary: We leverage the idea of model extraction to guide the learned steering vectors to approximate the ideal one.<n> Experiments demonstrate that our method notably improves the effectiveness and robustness of probe-based steering.
Score: 45.44490652074352
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of steering strength, limiting their robustness and effectiveness. In this paper, we leverage the idea of model extraction to guide the learned steering vectors to approximate the ideal one and propose tuning the steering strength adaptively based on contrastive activations' statistics. Experiments demonstrate that our method notably improves the effectiveness and robustness of probe-based steering, without any extra contrastive prompts or laborious manual tuning. Being an attack paper, this paper focuses on revealing the breakdown of fortified LLMs, raising the average harmfulness score from 6\% to 70\%. Our code is available at https://github.com/fhdnskfbeuv/adaptiveSteering.

Related papers

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection [8.819278296219071]
Large Language Models (LLMs) often fail to follow complex user instructions.<n> Activation steering techniques aim to manipulate model internals, but have a potential risk of oversteering.<n>We introduce DIRECTER, a novel steering method that dynamically modulates steering strength by scaling the KV cache without extra dataset.
arXiv Detail & Related papers (2026-03-06T09:49:32Z)
AMPS: Adaptive Modality Preference Steering via Functional Entropy [66.69992693275061]
We introduce an instance-aware diagnostic metric that quantifies each modality's information contribution and reveals sample-specific susceptibility to steering.<n> Experimental results show that our instance-aware steering outperforms conventional steering in modulating modality preference.
arXiv Detail & Related papers (2026-02-13T02:29:06Z)
ATLAS: Adaptive Test-Time Latent Steering with External Verifiers for Enhancing LLMs Reasoning [13.073472989807675]
We propose Adaptive Test-time Latent Steering, called (ATLAS)<n>ATLAS dynamically controls steering decisions at inference time using an external, lightweight latent verifier.<n> Experiments on multiple mathematical reasoning benchmarks show that ATLAS consistently outperforms both vanilla decoding and fixed steering baselines.
arXiv Detail & Related papers (2026-01-06T15:27:24Z)
AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint [49.641959856967276]
We present a theoretically grounded and empirically effective activation steering method called AlphaSteer.<n>For utility preservation, it learns to construct a nearly zero vector for steering benign data, with the null-space constraints.<n>Experiments across multiple jailbreak attacks and utility benchmarks demonstrate the effectiveness of AlphaSteer.
arXiv Detail & Related papers (2025-06-08T07:03:28Z)
Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs [8.085475675888045]
Activation steering provides an alternative for inference-time control.<n>We introduce a novel approach using a lightweight, trainable controller network integrated during inference.
arXiv Detail & Related papers (2025-05-22T01:48:38Z)
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender [99.3105257001476]
We propose AdaSteer, an adaptive activation steering method that adjusts model behavior based on input characteristics.<n>AdaSteer steers input representations along both the Rejection Direction (RD) and Harmfulness Direction (HD)<n>Our results highlight the potential of interpretable model internals for real-time, flexible safety enforcement in LLMs.
arXiv Detail & Related papers (2025-04-13T07:39:17Z)
Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks [16.508109544083496]
Vision Language Models (VLMs) can produce unintended and harmful content when exposed to adversarial attacks.<n>Existing defenses, such as input preprocessing, adversarial training, and response evaluation-based methods, are often impractical for real-world deployment.<n>We propose ASTRA, an efficient and effective defense by adaptively steering models away from adversarial feature directions to resist VLM attacks.
arXiv Detail & Related papers (2024-11-23T02:17:17Z)
Steering Without Side Effects: Improving Post-Deployment Control of Language Models [61.99293520621248]
Language models (LMs) have been shown to behave unexpectedly post-deployment. We present KL-then-steer (KTS), a technique that decreases the side effects of steering while retaining its benefits. Our best method prevents 44% of jailbreak attacks compared to the original Llama-2-chat-7B model.
arXiv Detail & Related papers (2024-06-21T01:37:39Z)
InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
arXiv Detail & Related papers (2024-01-20T10:41:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.