AI Paper Atlas

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

Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception

Yihang Tao, Senkang Hu, Haonan An, Zhengru Fang, Hangcheng Cao, Yuguang Fang

CVPR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Attacks and defenses in sequential settings · 5 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
use MVIG spoof attack instead of RC (spoof) against CADMVIG attack · Adv-OPV2V spoofing, CAD defenseDSR: 83.5 -> 32.0Improved
use MVIG removal attack instead of RC (remove) against CADMVIG attack · Adv-OPV2V removal, CAD defenseDSR: 90.1 -> 78.2Improved
use MVIG spoof instead of RC (spoof) against ROBOSACMVIG attack · Adv-OPV2V spoofing, ROBOSAC defenseDSR: 12.0 -> 14.8Hurt
use MVIG spoof instead of RC (spoof) against GCPMVIG attack · Adv-OPV2V spoofing, GCP defenseDSR: 12.2 -> 13.0Hurt
use MVIG spoof instead of RC (spoof) against CP-GuardMVIG attack · Adv-OPV2V spoofing, CP-Guard defenseDSR: 18.1 -> 17.2No clear effect
use MVIG removal instead of RC (remove) against CP-GuardMVIG attack · Adv-OPV2V removal, CP-Guard defenseDSR: 21.4 -> 21.3No clear effect
extend attack to 3-frame persistence with MVIG vs RC against CADMVIG attack · Adv-OPV2V spoofing, CAD defense, 3-frame persistenceDSR: 100.0 -> 63.2Improved
increase persistence from 0-frame to 3-frame for RC (spoof)RC (spoof) baseline · CAD defenseDSR: 83.5 -> 100.0Hurt
enlarge impacted zone from 15m to 50m for spoof attack (ablation)MVIG (spoof) · CAD defenseDSR (%): 40.2% -> 14.8%Improved
enlarge impacted zone for removal attack (ablation)MVIG (remove) · CAD defenseDSR (%): between 72.1% and 84.5%No clear effect
add attack continuation threshold (0.35 to 0.55) instead of none (ablation)MVIG (spoof) · CAD defenseDSR (%): 85.3% -> lowerImproved
use MVIG instead of RC at higher persistence against ROBOSAC+ for removalMVIG (remove) · ROBOSAC+ 1-frame persistenceDSR: 28.1 -> 32.5Hurt

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