# Delta-Influence: Unlearning Poisons via Influence Functions

arXiv: https://arxiv.org/abs/2411.13731 · HTML: https://mlsanity.com/paper/2411.13731/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- First posted on arXiv 20 Nov 2024.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Built on by (most cited first, 13 of 13)

- [Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning](https://mlsanity.com/paper/2412.08559/) (2024)
- [IF-GUIDE: Influence Function-Guided Detoxification of LLMs](https://mlsanity.com/paper/2506.01790/) (2025)
- [Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions](https://mlsanity.com/paper/2602.09987/) (2026)
- [Scalable Valuation of Human Feedback through Provably Robust Model Alignment](https://mlsanity.com/paper/2505.17859/) (2025)
- [A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks](https://mlsanity.com/paper/2412.00789/) (2024)
- [Reveal and Release: Iterative LLM Unlearning with Self-generated Data](https://mlsanity.com/paper/2509.14624/) (2025)
- [Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities](https://mlsanity.com/paper/2601.21702/) (2026)
- [ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curation](https://mlsanity.com/paper/2606.16208/) (2026)
- [Soft Weighted Machine Unlearning](https://mlsanity.com/paper/2505.18783/) (2025)
- [Targeted Fine-Tuning of DNN-Based Receivers via Influence Functions](https://mlsanity.com/paper/2509.15950/) (2025)
- [Adaptive Data Selection for Multi-Layer Perceptron Training: A Sub-linear Value-Driven Method](https://mlsanity.com/paper/2510.21286/) (2025)
- [Correlation-Guided Fast Machine Unlearning via Hessian Analysis](https://mlsanity.com/paper/2609.12620/) (2026)
- [Steering by Influence: Curvature Aware Data Weighting for Activation Steering](https://mlsanity.com/paper/2610.06383/) (2026)

## Abstract (arXiv)

Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. State-of-the-art influence functions, such as EK-FAC and TRAK, often fail to accurately attribute abnormal model behavior to the specific poisoned training data responsible for the data poisoning attack. In addition, traditional unlearning algorithms often struggle to effectively remove the influence of poisoned samples, particularly when only a few affected examples can be identified. To address these challenge, we introduce Delta-Influence, a novel approach that leverages influence functions to trace abnormal model behavior back to the responsible poisoned training data using as little as just one poisoned test example. Delta-Influence applies data transformations that sever the link between poisoned training data and compromised test points without significantly affecting clean data. This allows Delta-Influence to detect large negative shifts in influence scores following data transformations, a phenomenon we term as influence collapse, thereby accurately identifying poisoned training data. Unlearning this subset, e.g. through retraining, effectively eliminates the data poisoning. We validate our method across three vision-based poisoning attacks and three datasets, benchmarking against five detection algorithms and five unlearning strategies. We show that Delta-Influence consistently achieves the best unlearning across all settings, showing the promise of influence functions for corrective unlearning. Our code is publicly available at: https://github.com/Ruby-a07/delta-influence