# Interpreting Vulnerabilities of Multi-Instance Learning to Adversarial Perturbations

arXiv: https://arxiv.org/abs/2211.17071 · HTML: https://mlsanity.com/paper/2211.17071/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Builds on (most cited first, 19 of 19)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Adversarial Attacks and Defenses in Images, Graphs and Text: A Review](https://mlsanity.com/paper/1909.08072/) (2019)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection](https://mlsanity.com/paper/1903.07256/) (2019)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Weakly Supervised Action Localization by Sparse Temporal Pooling Network](https://mlsanity.com/paper/1712.05080/) (2017)
- [Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2103.10626/) (2021)
- [Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm](https://mlsanity.com/paper/2106.06027/) (2021)
- [Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction](https://mlsanity.com/paper/2204.09204/) (2022)
- [Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations](https://mlsanity.com/paper/2009.13714/) (2020)
- [Multi-Attention Multiple Instance Learning](https://mlsanity.com/paper/2112.06071/) (2021)
- [HAMIL: Hierarchical Aggregation-Based Multi-Instance Learning for Microscopy Image Classification](https://mlsanity.com/paper/2103.09764/) (2021)

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

- [Vision-Language Models Assisted Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2409.14109/) (2024)
- [Data-driven Knowledge Fusion for Deep Multi-instance Learning](https://mlsanity.com/paper/2304.11905/) (2023)
- [Towards Cross-Domain Multi-Targeted Adversarial Attacks](https://mlsanity.com/paper/2505.20782/) (2025)

## Abstract (arXiv)

Multi-Instance Learning (MIL) is a recent machine learning paradigm which is immensely useful in various real-life applications, like image analysis, video anomaly detection, text classification, etc. It is well known that most of the existing machine learning classifiers are highly vulnerable to adversarial perturbations. Since MIL is a weakly supervised learning, where information is available for a set of instances, called bag and not for every instances, adversarial perturbations can be fatal. In this paper, we have proposed two adversarial perturbation methods to analyze the effect of adversarial perturbations to interpret the vulnerability of MIL methods. Out of the two algorithms, one can be customized for every bag, and the other is a universal one, which can affect all bags in a given data set and thus has some generalizability. Through simulations, we have also shown the effectiveness of the proposed algorithms to fool the state-of-the-art (SOTA) MIL methods. Finally, we have discussed through experiments, about taking care of these kind of adversarial perturbations through a simple strategy. Source codes are available at https://github.com/InkiInki/MI-UAP.