# CSC: Turning the Adversary's Poison against Itself

arXiv: https://arxiv.org/abs/2604.21416 · HTML: https://mlsanity.com/paper/2604.21416/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## 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, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [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)
- [Input-Aware Dynamic Backdoor Attack](https://mlsanity.com/paper/2010.08138/) (2020)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [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)
- [Backdoor Defense via Decoupling the Training Process](https://mlsanity.com/paper/2202.03423/) (2022)
- [Transferable Clean-Label Poisoning Attacks on Deep Neural Nets](https://mlsanity.com/paper/1905.05897/) (2019)
- [A Survey of Deep Learning Applications to Autonomous Vehicle Control](https://mlsanity.com/paper/1912.10773/) (2019)
- [On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping](https://mlsanity.com/paper/2002.11497/) (2020)
- [Backdoor Defense via Adaptively Splitting Poisoned Dataset](https://mlsanity.com/paper/2303.12993/) (2023)
- [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)
- [QUEEN: Query Unlearning against Model Extraction](https://mlsanity.com/paper/2407.01251/) (2024)
- [Turning Black Box into White Box: Dataset Distillation Leaks](https://mlsanity.com/paper/2603.01053/) (2026)
- [Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction](https://mlsanity.com/paper/2603.01067/) (2026)
- [Osmosis Distillation: Model Hijacking with the Fewest Samples](https://mlsanity.com/paper/2603.04859/) (2026)

## Abstract (arXiv)

Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversary-specified labels while maintaining performance on clean data. Existing poison restraint-based defenses often suffer from inadequate detection against specific attack variants and compromise model utility through unlearning methods that lead to accuracy degradation. This paper conducts a comprehensive analysis of backdoor attack dynamics during model training, revealing that poisoned samples form isolated clusters in latent space early on, with triggers acting as dominant features distinct from benign ones. Leveraging these insights, we propose Cluster Segregation Concealment (CSC), a novel poison suppression defense. CSC first trains a deep neural network via standard supervised learning while segregating poisoned samples through feature extraction from early epochs, DBSCAN clustering, and identification of anomalous clusters based on class diversity and density metrics. In the concealment stage, identified poisoned samples are relabeled to a virtual class, and the model's classifier is fine-tuned using cross-entropy loss to replace the backdoor association with a benign virtual linkage, preserving overall accuracy. CSC was evaluated on four benchmark datasets against twelve poisoning-based attacks, CSC outperforms nine state-of-the-art defenses by reducing average attack success rates to near zero with minimal clean accuracy loss. Contributions include robust backdoor patterns identification, an effective concealment mechanism, and superior empirical validation, advancing trustworthy artificial intelligence.