AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

AdvDO: Realistic Adversarial Attacks for Trajectory Prediction

Yulong Cao, Chaowei Xiao, Anima Anandkumar, Danfei Xu, Marco Pavone

ECCV 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 87 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 with Opt-init instead of corrected search*AgentFormer w/ map · nuScenes valADE: 1.88 -> 3.39Improved
free the current dynamics (Opt-init) rather than fixing them (Opt-end) (ablation)AgentFormer w/ map · nuScenes valADE: 2.23 -> 3.39Improved
Opt-init vs Opt-end on Trajectron++ w/o map (ablation)Trajectron++ w/o map · nuScenes valMR: 49.5% -> 76.8%Improved
use unbounded search attack instead of curvature-bounded search* (ablation)AgentFormer w/ map · nuScenes valviolation rate: 0% -> 10%Hurt
remove the map input from AgentFormer (ablation)AgentFormer · nuScenes val under Opt-initADE: 3.39 -> 3.81Hurt
evaluate with planning-aware weightingAgentFormer w/ map · nuScenes valPI-ADE: 1.38 -> 2.05Improved
adversarially train on Opt-init attack instead of search attack (ablation)AgentFormer w/ map · nuScenes valADE on Opt-init attack: 2.81 -> 2.54Improved
adversarial training of any kind on clean data (ablation)AgentFormer w/ map · nuScenes val benignADE: 1.83 -> 2.38Hurt
add AdvDO-generated data augmentation (ablation)AgentFormer · nuScenes val benignADE: 1.83 -> 1.69Improved
compare generated trajectory sensitivity change of Opt-end versus searchAgentFormer w/ map · nuScenes valDelta sensitivity: 2.33 -> 1.12Improved
attack of closed-loop planning with MPC rather than rule-based plannerPlanner · nuScenes subsetcollisions: 12/150 -> 7/150Improved
closed-loop instead of open-loop planningMPC planner · nuScenes subsetoff road: 43/150 -> 23/150Improved

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