Backdooring Masked Diffusion Language Models

• URL: http://arxiv.org/abs/2605.19262v1
• Date: Tue, 19 May 2026 02:20:08 GMT
• Title: Backdooring Masked Diffusion Language Models
• Abstract summary: We present the first systematic study of training-time backdoor attacks on MDLMs.<n>We propose SHADOWMASK, a backdoor attack that modifies the MDLM forward corruption process.<n> Evaluations on DiT-based MDLM and LLaDA-8B-Instruct across WikiText-103, OpenWebText, and Alpaca show that SHADOWMASK achieves near-100% attack success.
• Score: 46.57066684106858
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs rely on discrete state corruption and iterative denoising rather than continuous noising or left-to-right prediction. In this work, we present the first systematic study of training-time backdoor attacks on MDLMs. We propose SHADOWMASK, a backdoor attack that modifies the MDLM forward corruption process by replacing the standard all-mask terminal distribution with a trigger-mask mixture prior. This creates a dedicated denoising pathway from trigger-corrupted states to attacker-specified targets while preserving clean denoising behavior. We further provide a principled mathematical formulation by defining the backdoored forward process, deriving the reverse-time posterior, and obtaining the continuous-time training objective. Evaluations on DiT-based MDLM and LLaDA-8B-Instruct across WikiText-103, OpenWebText, and Alpaca show that SHADOWMASK achieves near-100% attack success, substantially outperforms standard data poisoning, largely preserves clean utility, remains effective under full-model and parameter-efficient fine-tuning, and is robust against representative defenses.

Related papers

• BadDLM: Backdooring Diffusion Language Models with Diverse Targets [35.316538349611406]
  Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models.<n>We propose BadDLM, a unified framework for studying backdoor attacks against DLMs with diverse targets.<n>Our findings expose a new class of security risks in diffusion-based language generation and call for defenses tailored to DLM denoising dynamics.
  arXiv  Detail & Related papers  (2026-05-10T07:50:02Z)
• Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models [74.1970982768771]
  We show that well-established data-poisoning pipelines can successfully implant backdoors into MDLMs.<n>We introduce a backdoor defense framework for MDLMs named DiSP (Diffusion Self-Purification)
  arXiv  Detail & Related papers  (2026-02-24T15:47:52Z)
• Membership Inference Attacks Against Fine-tuned Diffusion Language Models [14.835693946869178]
  Diffusion Language Models (DLMs) are a promising alternative to autoregressive language models.<n>This paper presents the first systematic investigation of Membership Inference Attacks (MIA) vulnerabilities in DLMs.<n>We introduce SAMA (Subset-Aggregated Membership Attack), which addresses the sparse signal challenge through robust aggregation.
  arXiv  Detail & Related papers  (2026-01-27T23:40:07Z)
• 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)
• 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)
• Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models [3.134071086568745]
  Diffusion models (DMs) are regarded as one of the most advanced generative models today. Recent studies suggest that DMs are vulnerable to backdoor attacks. This vulnerability poses substantial risks, including reputational damage to model owners. We introduce Diff-Cleanse, a novel two-stage backdoor defense framework specifically designed for DMs.
  arXiv  Detail & Related papers  (2024-07-31T03:54:41Z)
• 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)
• Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots [68.84056762301329]
  Recent research has exposed the susceptibility of pretrained language models (PLMs) to backdoor attacks. We propose and integrate a honeypot module into the original PLM to absorb backdoor information exclusively. Our design is motivated by the observation that lower-layer representations in PLMs carry sufficient backdoor features.
  arXiv  Detail & Related papers  (2023-10-28T08:21:16Z)
• VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models [69.20464255450788]
  Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. Recent studies have shown that basic unconditional DMs are vulnerable to backdoor injection. This paper presents a unified backdoor attack framework to expand the current scope of backdoor analysis for DMs.
  arXiv  Detail & Related papers  (2023-06-12T05:14:13Z)

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.