# Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets

arXiv: https://arxiv.org/abs/2504.11990 · HTML: https://mlsanity.com/paper/2504.11990/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 37 of its 65 references that are in the map.
- First posted on arXiv 16 Apr 2025.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 30 of 37)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [STRIP: A Defence Against Trojan Attacks on Deep Neural Networks](https://mlsanity.com/paper/1902.06531/) (2019)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Anti-Backdoor Learning: Training Clean Models on Poisoned Data](https://mlsanity.com/paper/2110.11571/) (2021)
- [A new Backdoor Attack in CNNs by training set corruption without label poisoning](https://mlsanity.com/paper/1902.11237/) (2019)
- [Adversarial Unlearning of Backdoors via Implicit Hypergradient](https://mlsanity.com/paper/2110.03735/) (2021)
- [Backdoor Defense via Decoupling the Training Process](https://mlsanity.com/paper/2202.03423/) (2022)
- [SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics](https://mlsanity.com/paper/2104.11315/) (2021)
- [Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection](https://mlsanity.com/paper/1908.00686/) (2019)
- [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)
- [Backdoor Scanning for Deep Neural Networks through K-Arm Optimization](https://mlsanity.com/paper/2102.05123/) (2021)
- [SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency](https://mlsanity.com/paper/2302.03251/) (2023)
- [Backdoor Attacks on Self-Supervised Learning](https://mlsanity.com/paper/2105.10123/) (2021)
- [Backdoor Attack in the Physical World](https://mlsanity.com/paper/2104.02361/) (2021)
- [Data-free Backdoor Removal based on Channel Lipschitzness](https://mlsanity.com/paper/2208.03111/) (2022)
- [DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation](https://mlsanity.com/paper/2012.07006/) (2020)
- [Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization](https://mlsanity.com/paper/2304.11823/) (2023)
- [The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices](https://mlsanity.com/paper/2209.11715/) (2022)
- [Detecting Backdoors in Pre-trained Encoders](https://mlsanity.com/paper/2303.15180/) (2023)
- [Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency](https://mlsanity.com/paper/2303.18191/) (2023)
- [Backdoor Attacks against Transfer Learning with Pre-trained Deep Learning Models](https://mlsanity.com/paper/2001.03274/) (2020)
- [Backdoor Defense via Adaptively Splitting Poisoned Dataset](https://mlsanity.com/paper/2303.12993/) (2023)
- [Towards A Proactive ML Approach for Detecting Backdoor Poison Samples](https://mlsanity.com/paper/2205.13616/) (2022)
- [IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency](https://mlsanity.com/paper/2405.09786/) (2024)
- [Training with More Confidence: Mitigating Injected and Natural Backdoors During Training](https://mlsanity.com/paper/2202.06382/) (2022)
- [Backdoor Defense via Deconfounded Representation Learning](https://mlsanity.com/paper/2303.06818/) (2023)

## Built on by (most cited first, 3 of 3)

- [TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening](https://mlsanity.com/paper/2510.14299/) (2025)
- [Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content](https://mlsanity.com/paper/2605.29245/) (2026)
- [FIDA: Feature Instability-Driven Attack on Self-Supervised Facial Representation](https://mlsanity.com/paper/2608.26861/) (2026)

## Abstract (arXiv)

Transfer learning from pre-trained encoders has become essential in modern machine learning, enabling efficient model adaptation across diverse tasks. However, this combination of pre-training and downstream adaptation creates an expanded attack surface, exposing models to sophisticated backdoor embeddings at both the encoder and dataset levels--an area often overlooked in prior research. Additionally, the limited computational resources typically available to users of pre-trained encoders constrain the effectiveness of generic backdoor defenses compared to end-to-end training from scratch. In this work, we investigate how to mitigate potential backdoor risks in resource-constrained transfer learning scenarios. Specifically, we conduct an exhaustive analysis of existing defense strategies, revealing that many follow a reactive workflow based on assumptions that do not scale to unknown threats, novel attack types, or different training paradigms. In response, we introduce a proactive mindset focused on identifying clean elements and propose the Trusted Core (T-Core) Bootstrapping framework, which emphasizes the importance of pinpointing trustworthy data and neurons to enhance model security. Our empirical evaluations demonstrate the effectiveness and superiority of T-Core, specifically assessing 5 encoder poisoning attacks, 7 dataset poisoning attacks, and 14 baseline defenses across five benchmark datasets, addressing four scenarios of 3 potential backdoor threats.