MétaCan
Menu
Back to cohort
Record W4402727728 · doi:10.1109/cvpr52733.2024.01410

Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving

2024· article· en· W4402727728 on OpenAlexaff
Mozhgan Pourkeshavarz, Mohammad Sabokrou, Amir Rasouli

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicAutonomous Vehicle Technology and Safety
Canadian institutionsHuawei Technologies (Canada)
Fundersnot available
KeywordsBackdoorTrajectoryAdversarial systemComputer scienceComputer securityArtificial intelligenceMachine learningPhysics

Abstract

fetched live from OpenAlex

In autonomous driving, behavior prediction is funda-mental for safe motion planning, hence the security and ro-bustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adver-sarial backdoor attack against trajectory prediction models as a means of studying their potential vulnerabilities. Our attack affects the victim at training time via naturalistic, hence stealthy, poisoned samples crafted using a novel two-step approach. First, the triggers are crafted by perturbing the trajectory of attacking vehicle and then disguised by transforming the scene using a bi-level optimization technique. The proposed attack does not depend on a particu-lar model architecture and operates in a black-box manner, thus can be effective without any knowledge of the victim model. We conduct extensive empirical studies using state-of-the-art prediction models on two benchmark datasets using metrics customized for trajectory prediction. We show that the proposed attack is highly effective, as it can sig-nificantly hinder the performance of prediction models, un-noticeable by the victims, and efficient as it forces the vic-tim to generate malicious behavior even under constrained conditions. Via ablative studies, we analyze the impact of different attack design choices followed by an evaluation of existing defence mechanisms against the proposed attack.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.712
Threshold uncertainty score0.712

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.016
GPT teacher head0.245
Teacher spread0.229 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations15
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicAutonomous Vehicle Technology and SafetyFrench-language works237,207