Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures

• URL: http://arxiv.org/abs/2608.02271v1
• Date: Mon, 03 Aug 2026 14:10:54 GMT
• Title: Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures
• Abstract summary: Malicious actors can publish backdoored models that induce specific behaviors in response to predefined triggers.<n>We study the problem of weight-space backdoor detection, where a detector classifier predicts whether a model is malicious using only its weights.<n>We propose Z-PEFT, a lightweight meta-classifier that relies exclusively on layer-wise spectral measures for classification.
• Score: 19.105669683159302
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parameter-Efficient Fine-tuned (PEFT) models are frequently downloaded from open repositories by practitioners. This widespread practice creates a significant attack surface, as malicious actors can publish backdoored models that induce specific behaviors in response to predefined triggers. We study the problem of weight-space backdoor detection, where a detector classifier predicts whether a model is malicious using only its weights, enabling a lightweight safety mechanism. Most existing methods are designed and evaluated in a closed-world setting, where the detector is trained and tested on the same attack type. In contrast, we evaluate backdoor detection under novel conditions, including previously unseen attacks and datasets. We propose Z-PEFT, a lightweight meta-classifier that relies exclusively on layer-wise spectral measures for classification. Our experiments show that strong performance in the closed-world setting does not necessarily translate to high accuracy in zero-shot backdoor detection. Among weight-space detectors, Z-PEFT achieves the best performance while maintaining low and scalable computational cost.

Related papers

• Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift [35.70747932100589]
  DistScan is a backdoor detection framework based on a simple but previously unexploited observation.<n>It substantially outperforms existing methods, improving average detection accuracy over the best-performing applicable baseline by 27.32 percentage points.
  arXiv  Detail & Related papers  (2026-08-19T16:38:39Z)
• Lightweight and Fast Backdoor Model Detection [36.85393813658947]
  DFBScanner is a lightweight static parameter inspection framework for fast backdoor scanning.<n>We show that DFBScanner achieves a 97.17% true-positive rate, 0.95% false-positive rate, and an average detection time of only 1 ms per model.
  arXiv  Detail & Related papers  (2026-05-17T16:02:40Z)
• Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling [12.573852448122716]
  Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor security risks.<n>Existing defenses, particularly input-level methods, are more practical for deployment but often rely on observable anomalies that become unreliable under stealthy, semantics-preserving trigger designs.<n>We propose SET, an input-level backdoor detection framework that constructs response-offset features under multi-scale perturbations and learns a compact benign response space from a small set of clean samples.
  arXiv  Detail & Related papers  (2026-04-14T08:31:37Z)
• 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)
• Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution [49.78359632298156]
  Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks.<n> backdoor attacks, where models behave normally for standard queries but generate harmful responses or unintended output when specific triggers are activated.<n>We present LETHE, a novel method to eliminate backdoor behaviors from LLMs through knowledge dilution.
  arXiv  Detail & Related papers  (2025-08-28T17:05:18Z)
• 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)
• Defending against Indirect Prompt Injection by Instruction Detection [109.30156975159561]
  InstructDetector is a novel detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.<n>InstructDetector achieves a detection accuracy of 99.60% in the in-domain setting and 96.90% in the out-of-domain setting, and reduces the attack success rate to just 0.03% on the BIPIA benchmark.
  arXiv  Detail & Related papers  (2025-05-08T13:04:45Z)
• Evolutionary Trigger Detection and Lightweight Model Repair Based Backdoor Defense [10.310546695762467]
  Deep Neural Networks (DNNs) have been widely used in many areas such as autonomous driving and face recognition. A backdoor in the DNN model can be activated by a poisoned input with trigger and leads to wrong prediction. We propose an efficient backdoor defense based on evolutionary trigger detection and lightweight model repair.
  arXiv  Detail & Related papers  (2024-07-07T14:50:59Z)
• IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency [20.61046457594186]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. This paper proposes a simple yet effective input-level backdoor detection (dubbed IBD-PSC) to filter out malicious testing images.
  arXiv  Detail & Related papers  (2024-05-16T03:19:52Z)
• Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning [57.50274256088251]
  We show that parameter-efficient fine-tuning (PEFT) is more susceptible to weight-poisoning backdoor attacks. We develop a Poisoned Sample Identification Module (PSIM) leveraging PEFT, which identifies poisoned samples through confidence. We conduct experiments on text classification tasks, five fine-tuning strategies, and three weight-poisoning backdoor attack methods.
  arXiv  Detail & Related papers  (2024-02-19T14:22:54Z)
• Towards Stable Backdoor Purification through Feature Shift Tuning [22.529990213795216]
  Deep neural networks (DNN) are vulnerable to backdoor attacks. In this paper, we start with fine-tuning, one of the most common and easy-to-deploy backdoor defenses. We introduce Feature Shift Tuning (FST), a method for tuning-based backdoor purification.
  arXiv  Detail & Related papers  (2023-10-03T08:25:32Z)
• Adversarially Robust One-class Novelty Detection [83.1570537254877]
  We show that existing novelty detectors are susceptible to adversarial examples. We propose a defense strategy that manipulates the latent space of novelty detectors to improve the robustness against adversarial examples.
  arXiv  Detail & Related papers  (2021-08-25T10:41:29Z)

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.