MétaCan
Menu
Back to cohort
Record W4285601015 · doi:10.24963/ijcai.2022/433

Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future

2022· article· en· W4285601015 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueProceedings of the Thirty-First International Joint Conference on Artificial Intelligence · 2022
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsKootenay Association for Science & Technology
FundersOffice of Experimental Program to Stimulate Competitive ResearchMinistry of Science and ICT, South KoreaInstitute for Information and Communications Technology PromotionNational Science Foundation
KeywordsComputer scienceGeneralityHallucinatingRobustness (evolution)Vulnerability (computing)Adversarial systemComputer securityMachine learningArtificial intelligence

Abstract

fetched live from OpenAlex

Recurrent models are frequently being used in online tasks such as autonomous driving, and a comprehensive study of their vulnerability is called for. Existing research is limited in generality only addressing application-specific vulnerability or making implausible assumptions such as the knowledge of future input. In this paper, we present a general attack framework for online tasks incorporating the unique constraints of the online setting different from offline tasks. Our framework is versatile in that it covers time-varying adversarial objectives and various optimization constraints, allowing for a comprehensive study of robustness. Using the framework, we also present a novel white-box attack called Predictive Attack that `hallucinates' the future. The attack achieves 98 percent of the performance of the ideal but infeasible clairvoyant attack on average. We validate the effectiveness of the proposed framework and attacks through various experiments.

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.

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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.744
Threshold uncertainty score0.921

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0050.002
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 head0.072
GPT teacher head0.303
Teacher spread0.231 · 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