# PVF:Understanding AI Vulnerability Against SDCs

arXiv: https://arxiv.org/abs/2405.01741 · HTML: https://mlsanity.com/paper/2405.01741/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack](https://mlsanity.com/paper/1811.09310/) (2018)
- [Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search](https://mlsanity.com/paper/1903.12269/) (2019)
- [Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption](https://mlsanity.com/paper/2006.05620/) (2020)
- [MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendation](https://mlsanity.com/paper/2302.10872/) (2023)
- [Detecting silent data corruptions in the wild](https://mlsanity.com/paper/2203.08989/) (2022)

## Built on by (most cited first, 2 of 2)

- [FLARE: One-Shot PE-Level Fault Localization in Systolic Arrays via Algebraic Test Vectors](https://mlsanity.com/paper/2605.08594/) (2026)
- [Fault injection analysis of Real NVP normalising flow model for satellite anomaly detection](https://mlsanity.com/paper/2504.02015/) (2025)

## Abstract (arXiv)

Reliability of AI systems is a fundamental concern for the successful deployment and widespread adoption of AI technologies. Unfortunately, the escalating complexity and heterogeneity of AI hardware systems make them increasingly susceptible to hardware faults, e.g., silent data corruptions (SDC), that can potentially corrupt model parameters. When this occurs during AI inference/servicing, it can potentially lead to incorrect or degraded model output for users, ultimately affecting the quality and reliability of AI services. In light of the escalating threat, it is crucial to address key questions: How vulnerable are AI models to parameter corruptions, and how do different components (such as modules, layers) of the models exhibit varying vulnerabilities to parameter corruptions? To systematically address this question, we propose a novel quantitative metric, Parameter Vulnerability Factor (PVF), inspired by architectural vulnerability factor (AVF) in computer architecture community, aiming to standardize the quantification of AI model vulnerability against parameter corruptions. We define a model parameter's PVF as the probability that a corruption in that particular model parameter will result in an incorrect output. In this paper, we present several use cases on applying PVF to three types of tasks/models during inference -- recommendation (DLRM), vision classification (CNN), and text classification (BERT), while presenting an in-depth vulnerability analysis on DLRM. PVF has been a critical metric used for making key error management design decisions in productionizing Meta's in-house AI chip - MTIA.