# Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption

arXiv: https://arxiv.org/abs/2006.05620 · HTML: https://mlsanity.com/paper/2006.05620/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2020.

## Built on by (most cited first, 26 of 26)

- [ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks](https://mlsanity.com/paper/2102.11600/) (2021)
- [Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning](https://mlsanity.com/paper/2109.05687/) (2021)
- [Fisher SAM: Information Geometry and Sharpness Aware Minimisation](https://mlsanity.com/paper/2206.04920/) (2022)
- [Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models](https://mlsanity.com/paper/2210.09545/) (2022)
- [Machine Unlearning Fails to Remove Data Poisoning Attacks](https://mlsanity.com/paper/2406.17216/) (2024)
- [Loss-Curvature Matching for Dataset Selection and Condensation](https://mlsanity.com/paper/2303.04449/) (2023)
- [How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data](https://mlsanity.com/paper/2109.01300/) (2021)
- [Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks](https://mlsanity.com/paper/2303.03592/) (2023)
- [Versatile Weight Attack via Flipping Limited Bits](https://mlsanity.com/paper/2207.12405/) (2022)
- [GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization](https://mlsanity.com/paper/2210.06895/) (2022)
- [Adversarial Training Should Be Cast as a Non-Zero-Sum Game](https://mlsanity.com/paper/2306.11035/) (2023)
- [Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors](https://mlsanity.com/paper/2402.12626/) (2024)
- [Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability](https://mlsanity.com/paper/2108.01335/) (2021)
- [Adversarial Parameter Attack on Deep Neural Networks](https://mlsanity.com/paper/2203.10502/) (2022)
- [Minimum sharpness: Scale-invariant parameter-robustness of neural networks](https://mlsanity.com/paper/2106.12612/) (2021)
- [Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules](https://mlsanity.com/paper/2206.00823/) (2022)
- [Adversarial Parameter Defense by Multi-Step Risk Minimization](https://mlsanity.com/paper/2109.02889/) (2021)
- [FAM: Relative Flatness Aware Minimization](https://mlsanity.com/paper/2307.02337/) (2023)
- [PVF:Understanding AI Vulnerability Against SDCs](https://mlsanity.com/paper/2405.01741/) (2024)
- [Effective Gradient Sample Size via Variation Estimation for Accelerating Sharpness aware Minimization](https://mlsanity.com/paper/2403.08821/) (2024)
- [SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness](https://mlsanity.com/paper/2211.11561/) (2022)
- [Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search](https://mlsanity.com/paper/2405.06073/) (2024)
- [Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Security](https://mlsanity.com/paper/2409.11663/) (2024)
- [Are Targeted Data Poisoning Attacks as Effective as We Think?](https://mlsanity.com/paper/2509.06896/) (2025)
- [Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization](https://mlsanity.com/paper/2510.03763/) (2025)
- [NNV3: Expanding Neural Network Verification to New Architectures and Domains](https://mlsanity.com/paper/2609.30050/) (2026)

## Abstract (arXiv)

We argue that the vulnerability of model parameters is of crucial value to the study of model robustness and generalization but little research has been devoted to understanding this matter. In this work, we propose an indicator to measure the robustness of neural network parameters by exploiting their vulnerability via parameter corruption. The proposed indicator describes the maximum loss variation in the non-trivial worst-case scenario under parameter corruption. For practical purposes, we give a gradient-based estimation, which is far more effective than random corruption trials that can hardly induce the worst accuracy degradation. Equipped with theoretical support and empirical validation, we are able to systematically investigate the robustness of different model parameters and reveal vulnerability of deep neural networks that has been rarely paid attention to before. Moreover, we can enhance the models accordingly with the proposed adversarial corruption-resistant training, which not only improves the parameter robustness but also translates into accuracy elevation.