# Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation

arXiv: https://arxiv.org/abs/2107.11252 · HTML: https://mlsanity.com/paper/2107.11252/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 55 references that are in the map.
- First posted on arXiv 23 Jul 2021.

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [Visual Dialog](https://mlsanity.com/paper/1611.08669/) (2016)
- [Speaker-Follower Models for Vision-and-Language Navigation](https://mlsanity.com/paper/1806.02724/) (2018)
- [Embodied Question Answering](https://mlsanity.com/paper/1711.11543/) (2017)
- [REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments](https://mlsanity.com/paper/1904.10151/) (2019)
- [Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers](https://mlsanity.com/paper/1906.04584/) (2019)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [FreeLB: Enhanced Adversarial Training for Natural Language Understanding](https://mlsanity.com/paper/1909.11764/) (2019)
- [Image Captioning with Semantic Attention](https://mlsanity.com/paper/1603.03925/) (2016)
- [Vision-and-Dialog Navigation](https://mlsanity.com/paper/1907.04957/) (2019)
- [Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout](https://mlsanity.com/paper/1904.04195/) (2019)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments](https://mlsanity.com/paper/1811.12354/) (2018)
- [Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training](https://mlsanity.com/paper/2002.10638/) (2020)
- [Self-Monitoring Navigation Agent via Auxiliary Progress Estimation](https://mlsanity.com/paper/1901.03035/) (2019)
- [Certified Robustness to Adversarial Word Substitutions](https://mlsanity.com/paper/1909.00986/) (2019)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [GuessWhat?! Visual object discovery through multi-modal dialogue](https://mlsanity.com/paper/1611.08481/) (2016)
- [Adversarial Training for Large Neural Language Models](https://mlsanity.com/paper/2004.08994/) (2020)
- [Building Generalizable Agents with a Realistic and Rich 3D Environment](https://mlsanity.com/paper/1801.02209/) (2018)
- [Robust Neural Machine Translation with Doubly Adversarial Inputs](https://mlsanity.com/paper/1906.02443/) (2019)

## Built on by (most cited first, 15 of 15)

- [NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning](https://mlsanity.com/paper/2403.07376/) (2024)
- [GaussNav: Gaussian Splatting for Visual Navigation](https://mlsanity.com/paper/2403.11625/) (2024)
- [Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation](https://mlsanity.com/paper/2111.05759/) (2021)
- [DOROTHIE: Spoken Dialogue for Handling Unexpected Situations in Interactive Autonomous Driving Agents](https://mlsanity.com/paper/2210.12511/) (2022)
- [PASTS: Progress-Aware Spatio-Temporal Transformer Speaker For Vision-and-Language Navigation](https://mlsanity.com/paper/2305.11918/) (2023)
- [Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation](https://mlsanity.com/paper/2503.18065/) (2025)
- [Heterogeneous Embodied Multi-Agent Collaboration](https://mlsanity.com/paper/2307.13957/) (2023)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigation](https://mlsanity.com/paper/2510.16457/) (2025)
- [ULN: Towards Underspecified Vision-and-Language Navigation](https://mlsanity.com/paper/2210.10020/) (2022)
- [Trajectory-Diversity-Driven Robust Vision-and-Language Navigation](https://mlsanity.com/paper/2603.15370/) (2026)
- [CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models](https://mlsanity.com/paper/2603.22846/) (2026)
- [IntentionNav: A Benchmark for Intent-Driven Object Navigation from Implicit Human Instruction](https://mlsanity.com/paper/2605.23187/) (2026)
- [Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigation](https://mlsanity.com/paper/2403.03405/) (2024)
- [AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation](https://mlsanity.com/paper/2607.11063/) (2026)

## Abstract (arXiv)

Language instruction plays an essential role in the natural language grounded navigation tasks. However, navigators trained with limited human-annotated instructions may have difficulties in accurately capturing key information from the complicated instruction at different timesteps, leading to poor navigation performance. In this paper, we exploit to train a more robust navigator which is capable of dynamically extracting crucial factors from the long instruction, by using an adversarial attacking paradigm. Specifically, we propose a Dynamic Reinforced Instruction Attacker (DR-Attacker), which learns to mislead the navigator to move to the wrong target by destroying the most instructive information in instructions at different timesteps. By formulating the perturbation generation as a Markov Decision Process, DR-Attacker is optimized by the reinforcement learning algorithm to generate perturbed instructions sequentially during the navigation, according to a learnable attack score. Then, the perturbed instructions, which serve as hard samples, are used for improving the robustness of the navigator with an effective adversarial training strategy and an auxiliary self-supervised reasoning task. Experimental results on both Vision-and-Language Navigation (VLN) and Navigation from Dialog History (NDH) tasks show the superiority of our proposed method over state-of-the-art methods. Moreover, the visualization analysis shows the effectiveness of the proposed DR-Attacker, which can successfully attack crucial information in the instructions at different timesteps. Code is available at https://github.com/expectorlin/DR-Attacker.