Lune

ICLR2026Top-tier venue

Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion

Vishal Pramanik, Maisha Maliha, Susmit Jha, Sumit Kumar Jha

Abstract

Large language models remain vulnerable to jailbreak attacks, inputs crafted to bypass safety mechanisms and elicit harmful responses, despite advances in alignment and instruction tuning. Existing attacks often rely on prompt rewrites, dense optimization, or ad hoc heuristics, and lack interpretability and robustness. We propose Head-Masked Nullspace Steering (HMNS), a circuit-level intervention that (i) identifies attention heads most causally responsible for a model’s default behavior, (ii) suppresses their write paths via targeted column masking, and (iii) injects a perturbation constrained to the orthogonal complement of the muted subspace. This geometry-aware intervention preserves fluency while steering the model toward completions that differ from baseline routing. HMNS operates in a closed-loop detection–intervention cycle, re-identifying causal heads and reapplying interventions across multiple decoding attempts. Across multiple jailbreak benchmarks, strong safety defenses, and widely used language models, HMNS attains state-of-the-art attack success rates with fewer queries than prior methods. Ablations confirm that nullspace-constrained injection, residual norm scaling, and iterative re-identification are key to its effectiveness. To our knowledge, this is the first jailbreak method to leverage geometry-aware, interpretability-informed interventions, highlighting a new paradigm for controlled model steering and adversarial safety circumvention.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Tree of Attacks: Jailbreaking Black-Box LLMs Automatically cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
  • QLoRA: Efficient Finetuning of Quantized LLMs cites Training language models to follow instructions with human feedback
  • Direct Preference Optimization: Your Language Model is Secretly a Reward Model cites Training language models to follow instructions with human feedback
  • AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models cites Training language models to follow instructions with human feedback
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on19

  1. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  2. Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
  3. QLoRA: Efficient Finetuning of Quantized LLMsTim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke ZettlemoyerNeurIPS 2023 · 5,863 citations
  4. Tree of Attacks: Jailbreaking Black-Box LLMs AutomaticallyAnay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson et al.NeurIPS 2024 · 835 citations
  5. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language ModelsXiaogeng Liu, Nan Xu, Muhao Chen, Chaowei XiaoICLR 2024 · 722 citations

Related papers

  1. Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language ModelsXingyu Zhu, Beier Zhu, Shuo Wang, Junfeng Fang et al.CVPR 2026 · 5 citations
  2. Neuronal Insights into LLM Attacks: Targeted Neuron Tuning for Precise and Robust Vulnerability PatchingDan Shi, Renren Jin, Zhuowen Han, Yuqi Ren et al.ACL Findings 2026
  3. Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention HijackingJingru Li, Wei Ren, Tianqing ZhuACL 2026
  4. Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation MonitoringXiaohao Luo, Ying Wei, Rui ZhaoACL 2026
  5. FLASH: Focused Layer Attention Sink HijackingSiyuan Deng, Yerong Li, Fanhua Shang, Hongying LiuACL Findings 2026
Dusk over the sea between two cliffs drawn in fine vertical lines