# Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models

arXiv: https://arxiv.org/abs/2411.16512 · HTML: https://mlsanity.com/paper/2411.16512/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 25 Nov 2024.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Poisoning Language Models During Instruction Tuning](https://mlsanity.com/paper/2305.00944/) (2023)
- [Concept Bottleneck Model with Additional Unsupervised Concepts](https://mlsanity.com/paper/2202.01459/) (2022)
- [Interactive Concept Bottleneck Models](https://mlsanity.com/paper/2212.07430/) (2022)
- [BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning](https://mlsanity.com/paper/2105.00579/) (2021)
- [Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger](https://mlsanity.com/paper/2302.14677/) (2023)
- [Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models](https://mlsanity.com/paper/2310.03182/) (2023)
- [Label Poisoning is All You Need](https://mlsanity.com/paper/2310.18933/) (2023)
- [Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models](https://mlsanity.com/paper/2407.13934/) (2024)

## Built on by (most cited first, 3 of 3)

- [Robust Anomaly Detection in Network Traffic: Evaluating Machine Learning Models on CICIDS2017](https://mlsanity.com/paper/2506.19877/) (2025)
- [Backdooring CLIP through Concept Confusion](https://mlsanity.com/paper/2503.09095/) (2025)
- [VL-MedGuide: A Visual-Linguistic Large Model for Intelligent and Explainable Skin Disease Auxiliary Diagnosis](https://mlsanity.com/paper/2508.06624/) (2025)

## Abstract (arXiv)

The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medical diagnostics, where opaque models can undermine trust. Explainable Artificial Intelligence (XAI) aims to address these issues by providing clear, interpretable models. Among XAI techniques, Concept Bottleneck Models (CBMs) enhance transparency by using high-level semantic concepts. However, CBMs are vulnerable to concept-level backdoor attacks, which inject hidden triggers into these concepts, leading to undetectable anomalous behavior. To address this critical security gap, we introduce ConceptGuard, a novel defense framework specifically designed to protect CBMs from concept-level backdoor attacks. ConceptGuard employs a multi-stage approach, including concept clustering based on text distance measurements and a voting mechanism among classifiers trained on different concept subgroups, to isolate and mitigate potential triggers. Our contributions are threefold: (i) we present ConceptGuard as the first defense mechanism tailored for concept-level backdoor attacks in CBMs; (ii) we provide theoretical guarantees that ConceptGuard can effectively defend against such attacks within a certain trigger size threshold, ensuring robustness; and (iii) we demonstrate that ConceptGuard maintains the high performance and interpretability of CBMs, crucial for trustworthiness. Through comprehensive experiments and theoretical proofs, we show that ConceptGuard significantly enhances the security and trustworthiness of CBMs, paving the way for their secure deployment in critical applications.