AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Adversarial Attacks on Multi-Agent Communication

James Tu, Tsunhsuan Wang, Jingkang Wang, Sivabalan Manivasagam, Mengye Ren, Raquel Urtasun

ICCV 2021 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Learned inter-agent communication · 71 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
adversarially train against the white box feature-level attackermulti-agent detector · ShapeNet (perturbed)AP@0.7: 0.62 -> 66.00Improved
adversarially train against the white box feature-level attackerV2VNet · V2V (perturbed)AP@0.7: 7.55 -> 83.44Improved
adversarially train against the white box attacker (clean data)V2VNet · V2V (clean)AP@0.7: 82.19 -> 82.60Improved
train surrogate with domain adaptation (DA) for transfer attack (ablation)transfer attack · ShapeNet (2 agents)victim AP@0.7 (lower is stronger attack): 66.21 -> 42.59Improved
add ILAP projection on top of DA (ablation)transfer attack · ShapeNet (2 agents)victim AP@0.7: 42.59 -> 35.69Improved
add diversified inputs (DI) on top of DA (ablation)transfer attack · ShapeNet (2 agents)victim AP@0.7: 42.59 -> 49.38Hurt
reuse the previous perturbation across frames (ablation)online attack · V2V (2 agents)victim AP@0.7: 56.98 -> 7.55Improved
warp the perturbation with egomotion rigid transform (ablation)online attack · V2V (6 agents)victim AP@0.7: 77.37 -> 76.18Improved
use adversarial loss L_adv instead of negative task loss (ablation)white box attack · ShapeNet (2 agents)victim AP@0.7: 6.10 -> 0.37Improved
use adversarial loss L_adv instead of negative task loss (ablation)white box attack · V2V (2 agents)victim AP@0.7: 20.8 -> 7.55Improved
use GNN fusion instead of mean pooling for robustness (ablation)V2VNet · V2V (4 agents, perturbed)AP@0.7: 12.93 -> 52.31Improved
use median instead of mean pooling in GNN nodes (ablation)V2VNet · V2V (6 agents)AP@0.7 clean vs perturbed: 92.94 -> 90.75 clean; 76.18 -> 86.30 perturbedMixed

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