# Lilith: Backdoor Generalization under Training-Inference Trigger Shift

arXiv: https://arxiv.org/abs/2607.26099 · HTML: https://mlsanity.com/paper/2607.26099/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 60 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [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)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Invisible Backdoor Attack with Sample-Specific Triggers](https://mlsanity.com/paper/2012.03816/) (2020)
- [Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks](https://mlsanity.com/paper/2007.02343/) (2020)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Input-Aware Dynamic Backdoor Attack](https://mlsanity.com/paper/2010.08138/) (2020)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [Clean-Label Backdoor Attacks on Video Recognition Models](https://mlsanity.com/paper/2003.03030/) (2020)
- [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)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [Robust Large Margin Deep Neural Networks](https://mlsanity.com/paper/1605.08254/) (2016)
- [Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information](https://mlsanity.com/paper/2204.05255/) (2022)
- [Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch](https://mlsanity.com/paper/2106.08970/) (2021)
- [SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency](https://mlsanity.com/paper/2302.03251/) (2023)
- [Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1312.6082/) (2013)
- [Backdoor Attack in the Physical World](https://mlsanity.com/paper/2104.02361/) (2021)
- [Low Frequency Adversarial Perturbation](https://mlsanity.com/paper/1809.08758/) (2018)
- [Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency](https://mlsanity.com/paper/2303.18191/) (2023)
- [Black-box Backdoor Defense via Zero-shot Image Purification](https://mlsanity.com/paper/2303.12175/) (2023)
- [IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency](https://mlsanity.com/paper/2405.09786/) (2024)
- [Towards Stable Backdoor Purification through Feature Shift Tuning](https://mlsanity.com/paper/2310.01875/) (2023)
- [When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations](https://mlsanity.com/paper/2411.12701/) (2024)

## Abstract (arXiv)

Machine-learning services increasingly rely on public data, third-party providers, and outsourced training, creating opportunities for data-poisoning attacks that implant persistent malicious behavior while preserving benign utility. However, existing backdoor studies largely evaluate exact trigger reuse, training-exposed trigger diversity, or variations along predefined transformation axes. They therefore leave a critical blind spot: whether a backdoor learned from one training-time trigger can generalize to an inference-time trigger family absent from victim training. We formulate this problem as backdoor generalization under training--inference trigger shift and introduce Lilith, a black-box anchor-to-family framework. Using only disjoint surrogate resources, Lilith first induces a compact target-side vulnerability with a single training anchor, then constructs a bounded inference-only family that preserves the anchor-induced representation geometry. We characterize this mechanism through anchor clearance and family reach, deriving sufficient conditions for family-wise target preservation under local regularity and bounded surrogate--victim discrepancy. Experiments across datasets, architectures, poisoning rates, and defenses show that Lilith achieves high family-wise attack success with limited utility degradation and a small trigger generalization gap. Additional analyses show that family activation depends on representation alignment rather than the proposal mechanism, exposing a broader threat overlooked by exact-trigger evaluation.