# Adversarial Defense Through Network Profiling Based Path Extraction

arXiv: https://arxiv.org/abs/1904.08089 · HTML: https://mlsanity.com/paper/1904.08089/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 24 of 24)

- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation](https://mlsanity.com/paper/2202.07471/) (2022)
- [ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization](https://mlsanity.com/paper/2208.14286/) (2022)
- [Neural Response Interpretation through the Lens of Critical Pathways](https://mlsanity.com/paper/2103.16886/) (2021)
- [Dual-side Sparse Tensor Core](https://mlsanity.com/paper/2105.09564/) (2021)
- [FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons](https://mlsanity.com/paper/2204.02567/) (2022)
- [Block-Skim: Efficient Question Answering for Transformer](https://mlsanity.com/paper/2112.08560/) (2021)
- [Attack to Fool and Explain Deep Networks](https://mlsanity.com/paper/2106.10606/) (2021)
- [M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type](https://mlsanity.com/paper/2502.18755/) (2025)
- [Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators](https://mlsanity.com/paper/2106.06575/) (2021)
- [FAIRER: Fairness as Decision Rationale Alignment](https://mlsanity.com/paper/2306.15299/) (2023)
- [How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts](https://mlsanity.com/paper/2207.01168/) (2022)
- [Rethinking Textual Adversarial Defense for Pre-trained Language Models](https://mlsanity.com/paper/2208.10251/) (2022)
- [An Adversarial Robustness Perspective on the Topology of Neural Networks](https://mlsanity.com/paper/2211.02675/) (2022)
- [Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training](https://mlsanity.com/paper/2209.10778/) (2022)
- [Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators](https://mlsanity.com/paper/2212.02649/) (2022)
- [IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks](https://mlsanity.com/paper/2310.11890/) (2023)
- [HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks](https://mlsanity.com/paper/2106.05825/) (2021)
- [DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning](https://mlsanity.com/paper/2208.00498/) (2022)
- [On-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations](https://mlsanity.com/paper/2401.09518/) (2024)
- [Class-Wise Federated Averaging for Efficient Personalization](https://mlsanity.com/paper/2406.07800/) (2024)
- [On Transfer-based Universal Attacks in Pure Black-box Setting](https://mlsanity.com/paper/2504.08866/) (2025)
- [Anomaly Detection Based on Critical Paths for Deep Neural Networks](https://mlsanity.com/paper/2505.14967/) (2025)

## Abstract (arXiv)

Recently, researchers have started decomposing deep neural network models according to their semantics or functions. Recent work has shown the effectiveness of decomposed functional blocks for defending adversarial attacks, which add small input perturbation to the input image to fool the DNN models. This work proposes a profiling-based method to decompose the DNN models to different functional blocks, which lead to the effective path as a new approach to exploring DNNs' internal organization. Specifically, the per-image effective path can be aggregated to the class-level effective path, through which we observe that adversarial images activate effective path different from normal images. We propose an effective path similarity-based method to detect adversarial images with an interpretable model, which achieve better accuracy and broader applicability than the state-of-the-art technique.