AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation

Bingqian Lin, Yi Zhu, Yanxin Long, Xiaodan Liang, Qixiang Ye, Liang Lin

TPAMI 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 24 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
attack instructions with DR-Attacker (ablation)Base Agent · R2R Val UnseenSR (%): 48.0 -> 46.6Hurt
attack instructions with DR-Attacker (ablation)Base Agent · CVDN Val Unseen (last answer, mixed)Goal Progress (m): 3.88 -> 1.95Hurt
add adversarial training with auxiliary task (ablation)Base Agent · R2R Val UnseenSR (%): 48.0 -> 49.6Improved
add finetuning on original data after adversarial training (ablation)Adversarial Training w auxiliary task · R2R Val UnseenSR (%): 49.6 -> 53.2Improved
add finetuning after adversarial training (ablation)Adversarial Training w auxiliary task · CVDN Val Unseen (last answer, mixed)Goal Progress (m): 3.90 -> 4.20Improved
add auxiliary self-supervised reasoning task (ablation)Finetune (Adversarial Training) · CVDN Val Unseen (last answer, mixed)Goal Progress (m): 4.08 -> 4.20Improved
add auxiliary self-supervised reasoning task (ablation)Finetune (Adversarial Training) · CVDN Val Unseen (last answer, oracle)Goal Progress (m): 3.37 -> 3.48Improved
use DR-Attacker instead of Static attacker in adversarial training (ablation)Adversarial Training · CVDN Val Unseen (last answer, mixed)Goal Progress (m): 3.97 -> 4.20Improved
use DR-Attacker instead of PWWS attacker in adversarial training (ablation)Adversarial Training · CVDN Val Unseen (last answer, mixed)Goal Progress (m): 3.09 -> 4.20Improved
use DR-Attacker instead of Heuristics attacker in direct attack (ablation)Direct Attack · CVDN Val Unseen (last answer, mixed)Goal Progress (m): 1.89 -> 1.95Mixed
use DR-Attacker instead of Static attack (ablation)Direct Attack · CVDN Val Unseen (last answer, oracle)Goal Progress (m): 1.71 -> 1.50Improved
compare with PREVALENT pretraining (large data, 8 V100)DR-Attacker method · NDH trainingTotal time (min): 1661 -> 471Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy