# ModalImmune: Immunity Driven Unlearning via Self Destructive Training

arXiv: https://arxiv.org/abs/2602.16197 · HTML: https://mlsanity.com/paper/2602.16197/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 29 of its 56 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 29 of 29)

- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Memory Fusion Network for Multi-view Sequential Learning](https://mlsanity.com/paper/1802.00927/) (2018)
- [On Information Gain and Regret Bounds in Gaussian Process Bandits](https://mlsanity.com/paper/2009.06966/) (2020)
- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation](https://mlsanity.com/paper/2203.02177/) (2022)
- [M3Care: Learning with Missing Modalities in Multimodal Healthcare Data](https://mlsanity.com/paper/2210.17292/) (2022)
- [UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition](https://mlsanity.com/paper/2211.11256/) (2022)
- [Multimodal Fusion on Low-quality Data: A Comprehensive Survey](https://mlsanity.com/paper/2404.18947/) (2024)
- [Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations](https://mlsanity.com/paper/2210.17444/) (2022)
- [Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2109.01797/) (2021)
- [Unified Multi-Modal Image Synthesis for Missing Modality Imputation](https://mlsanity.com/paper/2304.05340/) (2023)
- [Gradient Routing: Masking Gradients to Localize Computation in Neural Networks](https://mlsanity.com/paper/2410.04332/) (2024)
- [BiAdam: Fast Adaptive Bilevel Optimization Methods](https://mlsanity.com/paper/2106.11396/) (2021)
- [Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities](https://mlsanity.com/paper/2404.16456/) (2024)
- [MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization](https://mlsanity.com/paper/2412.12098/) (2024)
- [Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation](https://mlsanity.com/paper/2310.03986/) (2023)
- [A Closer Look at Multimodal Representation Collapse](https://mlsanity.com/paper/2505.22483/) (2025)
- [Towards Robust Multimodal Sentiment Analysis with Incomplete Data](https://mlsanity.com/paper/2409.20012/) (2024)
- [DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis](https://mlsanity.com/paper/2412.12225/) (2024)
- [Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition](https://mlsanity.com/paper/2407.05374/) (2024)
- [SimMLM: A Simple Framework for Multi-modal Learning with Missing Modality](https://mlsanity.com/paper/2507.19264/) (2025)
- [Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness](https://mlsanity.com/paper/2503.18445/) (2025)
- [Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning](https://mlsanity.com/paper/2411.02793/) (2024)
- [Enhancing Multimodal Entity and Relation Extraction with Variational Information Bottleneck](https://mlsanity.com/paper/2304.02328/) (2023)
- [Causal Bandits with General Causal Models and Interventions](https://mlsanity.com/paper/2403.00233/) (2024)
- [Learning Robust Self-attention Features for Speech Emotion Recognition with Label-adaptive Mixup](https://mlsanity.com/paper/2305.06273/) (2023)
- [HyDiscGAN: A Hybrid Distributed cGAN for Audio-Visual Privacy Preservation in Multimodal Sentiment Analysis](https://mlsanity.com/paper/2404.11938/) (2024)
- [Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer](https://mlsanity.com/paper/2211.08843/) (2022)
- [RoHyDR: Robust Hybrid Diffusion Recovery for Incomplete Multimodal Emotion Recognition](https://mlsanity.com/paper/2505.17501/) (2025)

## Built on by (most cited first, 1 of 1)

- [Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs](https://mlsanity.com/paper/2606.25758/) (2026)

## Abstract (arXiv)

Multimodal systems are vulnerable to partial or complete loss of input channels at deployment, which undermines reliability in real-world settings. This paper presents ModalImmune, a training framework that enforces modality immunity by intentionally and controllably collapsing selected modality information during training so the model learns joint representations that are robust to destructive modality influence. The framework combines a spectrum-adaptive collapse regularizer, an information-gain guided controller for targeted interventions, curvature-aware gradient masking to stabilize destructive updates, and a certified Neumann-truncated hyper-gradient procedure for automatic meta-parameter adaptation. Empirical evaluation on standard multimodal benchmarks demonstrates that ModalImmune improves resilience to modality removal and corruption while retaining convergence stability and reconstruction capacity.