Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors

• URL: http://arxiv.org/abs/2604.12359v1
• Date: Tue, 14 Apr 2026 06:48:33 GMT
• Title: Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
• Abstract summary: Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines.<n> adversaries can distribute backdoored checkpoints that behave normally under standard evaluation but jailbreak when a hidden trigger is present.<n>Recent post-hoc weight-editing methods offer an efficient approach to injecting such backdoors.
• Score: 48.881343993730844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain attack surface: adversaries can distribute backdoored checkpoints that behave normally under standard evaluation but jailbreak when a hidden trigger is present. Recent post-hoc weight-editing methods offer an efficient approach to injecting such backdoors by directly modifying model weights to map a trigger to an attacker-specified response. However, existing methods typically optimize a token-level mapping that forces an affirmative prefix (e.g., ``Sure''), which does not guarantee sustained harmful output -- the model may begin with apparent agreement yet revert to safety-aligned refusal within a few decoding steps. We address this reliability gap by shifting the backdoor objective from surface tokens to internal representations. We extract a steering vector that captures the difference between compliant and refusal behaviors, and compile it into a persistent weight modification that activates only when the trigger is present. To preserve stealthiness and benign utility, we impose a null-space constraint so that the injected edit remains dormant on clean inputs. The method is efficient, requiring only a small set of examples and admitting a closed-form solution. Across multiple safety-aligned LLMs and jailbreak benchmarks, our method achieves high triggered attack success while maintaining non-triggered safety and general utility.

Related papers

• Selective Safety Steering via Value-Filtered Decoding [54.87935112120107]
  Large language models (LLMs) are trained to align with human values, but their generations may still violate safety constraints.<n>Existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model.<n>We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of unsafe responses.
  arXiv  Detail & Related papers  (2026-05-14T12:13:08Z)
• Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors [9.503673758168693]
  Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records.<n>We exploit a practical but overlooked supply-chain vector -- model code camouflaged as standard architectural definitions.<n>We introduce a deterministic full-chain mechanism: it locks onto token-level secrets in dynamic computation flows via online tensor-rule matching.
  arXiv  Detail & Related papers  (2026-04-30T05:03:08Z)
• Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion [12.201783188544093]
  Head-Masked Nullspace Steering (HMNS) identifies attention heads most causally responsible for a model's default behavior.<n>This is the first jailbreak method to leverage geometry-aware, interpretability-informed interventions.
  arXiv  Detail & Related papers  (2026-04-11T19:19:05Z)
• Bag of Tricks for Subverting Reasoning-based Safety Guardrails [62.139297207938036]
  We present a bag of jailbreak methods that subvert the reasoning-based guardrails.<n>Our attacks span white-, gray-, and black-box settings and range from effortless template manipulations to fully automated optimization.
  arXiv  Detail & Related papers  (2025-10-13T16:16:44Z)
• Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models [75.29749026964154]
  Ourmethod reduces the average Attack Success Rate to 4.41% across multiple benchmarks.<n>Clean accuracy and utility are preserved within 0.5% of the original model.<n>The defense generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.
  arXiv  Detail & Related papers  (2025-10-11T15:47:35Z)
• ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack [22.48980625853356]
  Large language models (LLMs) exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes.<n>In this work, we introduce Activation-Scaling Guard (ASGuard), an insightful, mechanistically-informed framework that surgically mitigates this specific vulnerability.
  arXiv  Detail & Related papers  (2025-09-30T06:33:52Z)
• DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion [0.7351161122478707]
  Deep neural networks are vulnerable to Trojan (backdoor) attacks.<n> triggerAdaptive inversion reconstructs malicious "shortcut" patterns inserted by an adversary during training.<n>We propose a data-free, zero-shot trigger-inversion strategy that restricts the search space while avoiding strong assumptions on trigger appearance.
  arXiv  Detail & Related papers  (2025-07-30T16:31:13Z)
• Probing the Robustness of Large Language Models Safety to Latent Perturbations [30.16804362984161]
  Safety alignment is a key requirement for building reliable Artificial General Intelligence.<n>We observe that minor latent shifts can still trigger unsafe responses in aligned models.<n>We introduce Layer-wise Adversarial Patch Training(LAPT), a fine-tuning strategy that injects controlled perturbations into hidden representations during training.
  arXiv  Detail & Related papers  (2025-06-19T07:03:05Z)
• Robust Anti-Backdoor Instruction Tuning in LVLMs [53.766434746801366]
  We introduce a lightweight, certified-agnostic defense framework for large visual language models (LVLMs)<n>Our framework finetunes only adapter modules and text embedding layers under instruction tuning.<n>Experiments against seven attacks on Flickr30k and MSCOCO demonstrate that ours reduces their attack success rate to nearly zero.
  arXiv  Detail & Related papers  (2025-06-04T01:23:35Z)
• ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs [17.853862145962292]
  We introduce a novel backdoor attack that systematically bypasses system prompts. Our method achieves an attack success rate (ASR) of up to 99.50% while maintaining a clean accuracy (CACC) of 98.58%.
  arXiv  Detail & Related papers  (2024-10-05T02:58:20Z)
• BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models [57.5404308854535]
  Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. We present BEEAR, a mitigation approach leveraging the insight that backdoor triggers induce relatively uniform drifts in the model's embedding space. Our bi-level optimization method identifies universal embedding perturbations that elicit unwanted behaviors and adjusts the model parameters to reinforce safe behaviors against these perturbations.
  arXiv  Detail & Related papers  (2024-06-24T19:29:47Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.