MétaCan
Menu
Back to cohort
Record W3176864543 · doi:10.65109/rgis8995

Transferable Environment Poisoning: Training-time Attack on Reinforcement Learning

2021· article· en· W3176864543 on OpenAlexaff
Hang Xu, Rundong Wang, Lev Raizman, Zinovi Rabinovich

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsReinforcementTraining (meteorology)Reinforcement learningComputer scienceComputer securityPsychologyArtificial intelligenceSocial psychologyGeographyMeteorology

Abstract

fetched live from OpenAlex

Studying adversarial attacks on Reinforcement Learning (RL) agents has become a key aspect of developing robust, RL-based solutions. Test-time attacks, which target the post-learning performance of an RL agent's policy, have been well studied in both white- and black-box settings. More recently, however, state-of-the-art works have shifted to investigate training-time attacks on RL agents, i.e., forcing the learning process towards a target policy designed by the attacker. Alas, these SOTA works continue to rely on white-box settings and/or use a reward-poisoning approach. In contrast, this paper studies environment-dynamics poisoning attacks at training time. Furthermore, while environment-dynamics poisoning presumes a transfer-learning capable agent, it also allows us to expand our approach to black-box attacks. Our overall framework, inspired by hierarchical RL, seeks the minimal environment-dynamics manipulation that will prompt the momentary policy of the agent to change in a desired manner. We show the attack efficiency by comparing it with the reward-poisoning approach, and empirically demonstrate the transferability of the environment-poisoning attack strategy. Finally, we seek to exploit the transferability of the attack strategy to handle black-box settings.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.008
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.002
Threshold uncertainty score0.009

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.008
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.000
Science and technology studies0.0000.002
Scholarly communication0.0010.001
Open science0.0010.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0020.000

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 head0.034
GPT teacher head0.260
Teacher spread0.225 · 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 source (direct Gemma or distilled Codex), 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

Citations8
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicAdversarial Robustness in Machine LearningFrench-language works237,207