SpecGuard: Inference-Time Backdoor Detection For Free

• URL: http://arxiv.org/abs/2609.11799v1
• Date: Thu, 10 Sep 2026 16:51:59 GMT
• Title: SpecGuard: Inference-Time Backdoor Detection For Free
• Abstract summary: SpecGuard is an inference-time backdoor detector that repurposes speculative decoding at zero added model-computation cost.<n>It reliably detects triggered behavior, including stealthy cases where input-level filters are blind.
• Score: 11.670265492085328
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are often fine-tuned, shared, or downloaded from third parties, so a deployed model may carry a hidden backdoor that behaves normally on benign inputs but switches to attacker-controlled behavior when a secret trigger appears. While backdoors can be audited before deployment, runtime monitoring remains important for models that are frequently updated. The challenge is that LLM serving is latency-sensitive: existing inference-time detectors either rely on assumptions about the trigger form, which can fail on stealthy attacks, or require extra model computation, such as input perturbations or an additional generation pass. We introduce SpecGuard, an inference-time backdoor detector that repurposes speculative decoding at zero added model-computation cost. Speculative decoding speeds up inference by using a small draft model to propose tokens and a target model to verify them. We observe that this verification process already exposes a useful signal: when a backdoor is triggered, the target model shifts toward the attacker's behavior, while a clean draft model does not predict this shift, causing the draft-token acceptance rate to change. We formalize when this signal appears and show that an attacker who suppresses it must also weaken the backdoor. Across diverse backdoor types and model families, SpecGuard reliably detects triggered behavior, including stealthy cases where input-level filters are blind, while avoiding the extra generation cost of existing runtime detectors. Speculative decoding therefore doubles as a free, always-on signal for detecting backdoored LLM behavior.

Related papers

• QUACK! Making the (Rubber) Ducky Talk: A Systematic Study of Keystroke Dynamics for HID Injection Detection [60.105690843777666]
  We show that robust, privacy-preserving detection is achievable using lightweight models operating solely on timing features.<n>Our analysis reveals that attacker sophistication does not monotonically translate into improved evasion.
  arXiv  Detail & Related papers  (2026-04-17T08:53:24Z)
• Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models [71.44858461725893]
  Given a model fine-tuned by an untrusted third party, determining whether the model has been injected with a backdoor is a critical and challenging problem.<n>Existing detection methods usually rely on prior knowledge of training dataset, backdoor triggers and targets.<n>We introduce Assimilation Matters in DETection (AMDET), a novel model-level detection framework that operates without any such prior knowledge.
  arXiv  Detail & Related papers  (2025-11-29T06:20:00Z)
• 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)
• Signature in Code Backdoor Detection, how far are we? [10.384592712399828]
  We revisit the applicability of Spectral Signature-based defenses in the context of backdoor attacks on code models.<n>We find that the widely used setting of Spectral Signature in code backdoor detection is often suboptimal.<n>We discover a new proxy metric that can more accurately estimate the actual performance of Spectral Signature without model retraining after the defense.
  arXiv  Detail & Related papers  (2025-10-15T18:18:08Z)
• Backdoor Attack with Invisible Triggers Based on Model Architecture Modification [5.094386595197844]
  Traditional backdoor attacks involve injecting malicious samples with specific triggers into the training data.<n>More sophisticated attacks modify the model's architecture directly.<n>A novel backdoor attack method is presented in the paper.<n>It embeds the backdoor within the model's architecture and has the capability to generate inconspicuous and stealthy triggers.
  arXiv  Detail & Related papers  (2024-12-22T07:39:43Z)
• Twin Trigger Generative Networks for Backdoor Attacks against Object Detection [14.578800906364414]
  Object detectors, which are widely used in real-world applications, are vulnerable to backdoor attacks. Most research on backdoor attacks has focused on image classification, with limited investigation into object detection. We propose novel twin trigger generative networks to generate invisible triggers for implanting backdoors into models during training, and visible triggers for steady activation during inference.
  arXiv  Detail & Related papers  (2024-11-23T03:46:45Z)
• Rethinking Backdoor Detection Evaluation for Language Models [43.17245824430881]
  Backdoor attacks pose a major security risk for practitioners who depend on publicly released language models.<n>As a countermeasure, backdoor detection methods aim to detect whether a released model contains a backdoor.<n>While existing backdoor detection methods have high accuracy in detecting backdoored models on standard benchmarks, it is unclear whether they can robustly identify backdoors in the wild.
  arXiv  Detail & Related papers  (2024-08-31T09:19:39Z)
• Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks [63.269788236474234]
  We propose to use model pairs on open-set classification tasks for detecting backdoors. We show that this score, can be an indicator for the presence of a backdoor despite models being of different architectures. This technique allows for the detection of backdoors on models designed for open-set classification tasks, which is little studied in the literature.
  arXiv  Detail & Related papers  (2024-02-28T21:29:16Z)
• Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder [50.1394620328318]
  Existing backdoor defense methods often require accessing a few validation data and model parameters.<n>We propose blind backdoor defense with Masked AutoEncoder (BDMAE)<n>BDMAE detects possible local triggers using image structural similarity and label consistency between the test image and MAE restorations.
  arXiv  Detail & Related papers  (2023-03-27T19:23:33Z)
• Untargeted Backdoor Attack against Object Detection [69.63097724439886]
  We design a poison-only backdoor attack in an untargeted manner, based on task characteristics. We show that, once the backdoor is embedded into the target model by our attack, it can trick the model to lose detection of any object stamped with our trigger patterns.
  arXiv  Detail & Related papers  (2022-11-02T17:05:45Z)
• A temporal chrominance trigger for clean-label backdoor attack against anti-spoof rebroadcast detection [41.735725886912185]
  We propose a stealthy clean-label video backdoor attack against Deep Learning (DL)-based models. The injected backdoor does not affect spoofing detection in normal conditions, but induces a misclassification in the presence of a triggering signal. The effectiveness of the proposed backdoor attack and its generality are validated experimentally on different datasets.
  arXiv  Detail & Related papers  (2022-06-02T15:30:42Z)

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.