# BagFlip: A Certified Defense against Data Poisoning

arXiv: https://arxiv.org/abs/2205.13634 · HTML: https://mlsanity.com/paper/2205.13634/

## Key facts

- Cited by 19 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 32 of its 46 references that are in the map.
- First posted on arXiv 26 May 2022.

## 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 32)

- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [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)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (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)
- [Hidden Trigger Backdoor Attacks](https://mlsanity.com/paper/1910.00033/) (2019)
- [Attack of the Tails: Yes, You Really Can Backdoor Federated Learning](https://mlsanity.com/paper/2007.05084/) (2020)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models](https://mlsanity.com/paper/1804.04637/) (2018)
- [Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching](https://mlsanity.com/paper/2009.02276/) (2020)
- [Stronger Data Poisoning Attacks Break Data Sanitization Defenses](https://mlsanity.com/paper/1811.00741/) (2018)
- [Transferable Clean-Label Poisoning Attacks on Deep Neural Nets](https://mlsanity.com/paper/1905.05897/) (2019)
- [RAB: Provable Robustness Against Backdoor Attacks](https://mlsanity.com/paper/2003.08904/) (2020)
- [Deep Partition Aggregation: Provable Defense against General Poisoning Attacks](https://mlsanity.com/paper/2006.14768/) (2020)
- [Certified Robustness to Label-Flipping Attacks via Randomized Smoothing](https://mlsanity.com/paper/2002.03018/) (2020)
- [Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks](https://mlsanity.com/paper/2008.04495/) (2020)
- [Is feature selection secure against training data poisoning?](https://mlsanity.com/paper/1804.07933/) (2018)
- [Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution](https://mlsanity.com/paper/2106.06361/) (2021)
- [Defending Neural Backdoors via Generative Distribution Modeling](https://mlsanity.com/paper/1910.04749/) (2019)
- [Data Poisoning against Differentially-Private Learners: Attacks and Defenses](https://mlsanity.com/paper/1903.09860/) (2019)
- [On Certifying Robustness against Backdoor Attacks via Randomized Smoothing](https://mlsanity.com/paper/2002.11750/) (2020)
- [Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability](https://mlsanity.com/paper/2005.00191/) (2020)
- [Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers](https://mlsanity.com/paper/1906.04948/) (2019)
- [Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks](https://mlsanity.com/paper/2012.03765/) (2020)
- [Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness](https://mlsanity.com/paper/2002.03239/) (2020)
- [Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation](https://mlsanity.com/paper/2202.02628/) (2022)
- [Backdoors in Neural Models of Source Code](https://mlsanity.com/paper/2006.06841/) (2020)

## Built on by (most cited first, 19 of 19)

- [Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples](https://mlsanity.com/paper/2307.10562/) (2023)
- [Provably Unlearnable Data Examples](https://mlsanity.com/paper/2405.03316/) (2024)
- [CBD: A Certified Backdoor Detector Based on Local Dominant Probability](https://mlsanity.com/paper/2310.17498/) (2023)
- [Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs](https://mlsanity.com/paper/2404.00486/) (2024)
- [PECAN: A Deterministic Certified Defense Against Backdoor Attacks](https://mlsanity.com/paper/2301.11824/) (2023)
- [Relational DNN Verification With Cross Executional Bound Refinement](https://mlsanity.com/paper/2405.10143/) (2024)
- [Test-Time Multimodal Backdoor Detection by Contrastive Prompting](https://mlsanity.com/paper/2405.15269/) (2024)
- [Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks](https://mlsanity.com/paper/2407.10867/) (2024)
- [FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models](https://mlsanity.com/paper/2404.08631/) (2024)
- [Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning](https://mlsanity.com/paper/2502.16737/) (2025)
- [FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks](https://mlsanity.com/paper/2406.11522/) (2024)
- [Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks](https://mlsanity.com/paper/2305.09671/) (2023)
- [Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising](https://mlsanity.com/paper/2403.11981/) (2024)
- [Mendata: A Framework to Purify Manipulated Training Data](https://mlsanity.com/paper/2312.01281/) (2023)
- [MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs](https://mlsanity.com/paper/2412.10186/) (2024)
- [Robustness Certificates for Neural Networks Against Data Poisoning and Evasion Attacks](https://mlsanity.com/paper/2512.20865/) (2025)
- [Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning](https://mlsanity.com/paper/2604.11416/) (2026)
- [Detecting Trojaned DNNs via Spectral Regression Analysis](https://mlsanity.com/paper/2605.21146/) (2026)
- [Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy](https://mlsanity.com/paper/2605.21780/) (2026)

## Abstract (arXiv)

Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but not the test inputs, while in a backdoor attack the attacker can also modify test inputs. Existing model-agnostic defense approaches either cannot handle backdoor attacks or do not provide effective certificates (i.e., a proof of a defense). We present BagFlip, a model-agnostic certified approach that can effectively defend against both trigger-less and backdoor attacks. We evaluate BagFlip on image classification and malware detection datasets. BagFlip is equal to or more effective than the state-of-the-art approaches for trigger-less attacks and more effective than the state-of-the-art approaches for backdoor attacks.