Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors

• URL: http://arxiv.org/abs/2604.27426v1
• Date: Thu, 30 Apr 2026 05:03:08 GMT
• Title: Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
• Abstract summary: 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.
• Score: 9.503673758168693
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed as a privacy boundary, we reveal that compromised model code is sufficient to steal them. Current passive pretrained-weight poisoning attacks, while effective for natural language, fundamentally fail to capture such sparse high-entropy targets due to their reliance on probabilistic semantic prefixes. To bridge this gap, we identify and exploit a practical but overlooked supply-chain vector -- model code camouflaged as standard architectural definitions -- to realize a paradigm shift from passive weight poisoning to active execution hijacking. We introduce a deterministic full-chain memorization mechanism: it locks onto token-level secrets in dynamic computation flows via online tensor-rule matching, and leverages value-gradient decoupling to stealthily inject attack gradients, overcoming gradient drowning to force model memorization. Furthermore, we achieve, for the first time, attacker-verifiable secret stealing through black-box queries that precisely distinguishes true leakage from hallucination. Experiments demonstrate that our method achieves over 98\% Strict ASR without compromising the primary task, and can effectively bypass defense measures including DP-SGD, semantic auditing, and code auditing.

Related papers

• Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors [4.377640147713394]
  Post-hoc model explainers are widely deployed to audit models in high-stakes sensitive domains.<n>A few studies have examined potential attacks in the explainability pipeline.<n>We introduce a more potent white-box, gradient-regularized evasion attack framework.
  arXiv  Detail & Related papers  (2026-08-01T10:03:14Z)
• TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning [60.68349524623048]
  Decompositional jailbreaks pose a critical threat to large language models.<n>We present TwinGate, a stateful dual-encoder defense framework.<n>We construct a comprehensive dataset of over 3.62 million instructions spanning 8,600 distinct malicious intents.
  arXiv  Detail & Related papers  (2026-04-30T13:44:01Z)
• Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors [48.881343993730844]
  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.
  arXiv  Detail & Related papers  (2026-04-14T06:48:33Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models [62.87838888016534]
  Graph Foundation Models (GFMs) are pre-trained on diverse source domains and adapted to unseen targets.<n>Backdoor attacks against GFMs are non-trivial due to three key challenges.<n>We propose GFM-BA, a novel Backdoor Attack model against Graph Foundation Models.
  arXiv  Detail & Related papers  (2025-11-22T08:52:09Z)
• Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models [6.182793047410624]
  We investigate the internal behavior of backdoored pre-trained language models.<n>We propose an inference-time defense that constructs anomaly scores by combining token-level attention and gradient information.
  arXiv  Detail & Related papers  (2025-10-05T20:15:56Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• 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)
• Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference [16.893873979953593]
  We propose a novel clean-label backdoor-based approach for stealthy data auditing. Our approach employs an optimal trigger generated by a shadow model that mimics target model's behavior. The proposed method enables robust data auditing through blackbox access, achieving high attack success rates across diverse datasets.
  arXiv  Detail & Related papers  (2024-11-24T20:56:18Z)
• A Practical Trigger-Free Backdoor Attack on Neural Networks [33.426207982772226]
  We propose a trigger-free backdoor attack that does not require access to any training data. Specifically, we design a novel fine-tuning approach that incorporates the concept of malicious data into the concept of the attacker-specified class. The effectiveness, practicality, and stealthiness of the proposed attack are evaluated on three real-world datasets.
  arXiv  Detail & Related papers  (2024-08-21T08:53:36Z)

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.