# Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers

arXiv: https://arxiv.org/abs/2609.03139 · HTML: https://mlsanity.com/paper/2609.03139/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 55 references that are in the map.
- First posted on arXiv 2 Sep 2026.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [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)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)
- [FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts](https://mlsanity.com/paper/2311.05608/) (2023)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [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)
- [Dynamic Backdoor Attacks Against Machine Learning Models](https://mlsanity.com/paper/2003.03675/) (2020)
- [Backdoor Attacks Against Deep Learning Systems in the Physical World](https://mlsanity.com/paper/2006.14580/) (2020)
- [Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review](https://mlsanity.com/paper/2007.10760/) (2020)
- [SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency](https://mlsanity.com/paper/2302.03251/) (2023)
- [The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices](https://mlsanity.com/paper/2209.11715/) (2022)
- [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)
- [Backdoor Defense via Adaptively Splitting Poisoned Dataset](https://mlsanity.com/paper/2303.12993/) (2023)
- [Backdoor Defense via Deconfounded Representation Learning](https://mlsanity.com/paper/2303.06818/) (2023)
- [Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack](https://mlsanity.com/paper/2405.16134/) (2024)
- [Defense-Prefix for Preventing Typographic Attacks on CLIP](https://mlsanity.com/paper/2304.04512/) (2023)
- [REFINE: Inversion-Free Backdoor Defense via Model Reprogramming](https://mlsanity.com/paper/2502.18508/) (2025)
- [Backdoor Attack through Frequency Domain](https://mlsanity.com/paper/2111.10991/) (2021)

## Abstract (arXiv)

Deep neural networks (DNNs) are increasingly deployed in real-world vision systems, yet their predictions can be covertly manipulated by backdoor attacks, in which malicious triggers cause targeted misclassification while preserving high clean accuracy. Existing defenses often rely on model internals, training data, or clean validation samples, making them difficult to deploy when only black-box access to a trained model is available. We propose TRIM (Trigger Removal by Identifying Manipulated Regions), a deployment-oriented black-box defense that detects and selectively removes backdoor triggers at inference time without requiring model internals, training data, or clean samples. The key insight behind TRIM is to identify image regions that are responsible for anomalous model behavior and purify only those regions while preserving benign content. TRIM innovates via three key components: (i) region-based segmentation with deep feature representations, (ii) adaptive trigger discovery through inpainting and diffusion-based reconstruction to isolate regions responsible for misclassification---without assumptions about trigger type, shape, or location, and (iii) selective region purification that cleans poisoned regions while retaining benign content. To support practical deployment, TRIM further caches feature embeddings of previously identified triggers, enabling efficient recognition and avoiding redundant detection and purification. Extensive experiments across diverse datasets and backdoor types, including blended, sparse, varying-size, and multiple triggers, show that TRIM consistently outperforms existing black-box defenses, reducing attack success rates (ASR) to as low as 1.16% while preserving clean accuracy of up to 87.87%. These results demonstrate that effective backdoor mitigation is possible at inference time even when the defender has no access to any auxiliary data.