# Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

arXiv: https://arxiv.org/abs/2503.16872 · HTML: https://mlsanity.com/paper/2503.16872/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 60 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Invisible Backdoor Attack with Sample-Specific Triggers](https://mlsanity.com/paper/2012.03816/) (2020)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Detecting AI Trojans Using Meta Neural Analysis](https://mlsanity.com/paper/1910.03137/) (2019)
- [Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective](https://mlsanity.com/paper/2104.03413/) (2021)
- [BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning](https://mlsanity.com/paper/2108.00352/) (2021)
- [BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning](https://mlsanity.com/paper/2311.12075/) (2023)
- [From Captions to Visual Concepts and Back](https://mlsanity.com/paper/1411.4952/) (2014)
- [VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models](https://mlsanity.com/paper/2402.13851/) (2024)
- [MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic](https://mlsanity.com/paper/2205.06900/) (2022)
- [Detecting Backdoors in Pre-trained Encoders](https://mlsanity.com/paper/2303.15180/) (2023)
- [Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models](https://mlsanity.com/paper/2402.06659/) (2024)
- [UNICORN: A Unified Backdoor Trigger Inversion Framework](https://mlsanity.com/paper/2304.02786/) (2023)
- [Pre-trained Trojan Attacks for Visual Recognition](https://mlsanity.com/paper/2312.15172/) (2023)
- [Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection](https://mlsanity.com/paper/2402.11473/) (2024)
- [Diversifying the High-level Features for better Adversarial Transferability](https://mlsanity.com/paper/2304.10136/) (2023)
- [Compromising Embodied Agents with Contextual Backdoor Attacks](https://mlsanity.com/paper/2408.02882/) (2024)

## Built on by (most cited first, 6 of 6)

- [MTL-UE: Learning to Learn Nothing for Multi-Task Learning](https://mlsanity.com/paper/2505.05279/) (2025)
- [SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs](https://mlsanity.com/paper/2506.04743/) (2025)
- [BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning](https://mlsanity.com/paper/2602.17168/) (2026)
- [Targeted Bit-Flip Attacks on LLM-Based Agents](https://mlsanity.com/paper/2603.10042/) (2026)
- [A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models](https://mlsanity.com/paper/2604.04488/) (2026)
- [TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting](https://mlsanity.com/paper/2605.22365/) (2026)

## Abstract (arXiv)

Institutions with limited data and computing resources often outsource model training to third-party providers in a semi-honest setting, assuming adherence to prescribed training protocols with pre-defined learning paradigm (e.g., supervised or semi-supervised learning). However, this practice can introduce severe security risks, as adversaries may poison the training data to embed backdoors into the resulting model. Existing detection approaches predominantly rely on statistical analyses, which often fail to maintain universally accurate detection accuracy across different learning paradigms. To address this challenge, we propose a unified backdoor detection framework in the semi-honest setting that exploits cross-examination of model inconsistencies between two independent service providers. Specifically, we integrate central kernel alignment to enable robust feature similarity measurements across different model architectures and learning paradigms, thereby facilitating precise recovery and identification of backdoor triggers. We further introduce backdoor fine-tuning sensitivity analysis to distinguish backdoor triggers from adversarial perturbations, substantially reducing false positives. Extensive experiments demonstrate that our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines across supervised, semi-supervised, and autoregressive learning tasks, respectively. Notably, it is the first to effectively detect backdoors in multimodal large language models, further highlighting its broad applicability and advancing secure deep learning.