MétaCan
Menu
Back to cohort
Record W7128225249 · doi:10.1162/tacl.a.27

Investigating Adversarial Trigger Transfer in Large Language Models

2025· article· en· W7128225249 on OpenAlexaff
Nicholas Meade, Arkil Patel, Siva Reddy

Bibliographic record

VenueTransactions of the Association for Computational Linguistics · 2025
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsCanadian Institute for Advanced Research
Fundersnot available
KeywordsAdversarial systemSecurity tokenOffensiveRobustness (evolution)Language modelThreat modelLanguage understanding

Abstract

fetched live from OpenAlex

Abstract Recent work has developed optimization procedures to find token sequences, called adversarial triggers, which can elicit unsafe responses from aligned language models. These triggers are believed to be highly transferable, i.e., a trigger optimized on one model can jailbreak other models. In this paper, we concretely show that such adversarial triggers are not consistently transferable. We extensively investigate trigger transfer among 13 open models and observe poor and inconsistent transfer. Our experiments further reveal a significant difference in robustness to adversarial triggers between models Aligned by Preference Optimization (APO) and models Aligned by Fine-Tuning (AFT). We find that APO models are extremely hard to jailbreak even when the trigger is optimized directly on the model. On the other hand, while AFT models may appear safe on the surface, exhibiting refusals to a range of unsafe instructions, we show that they are highly susceptible to adversarial triggers. Lastly, we observe that most triggers optimized on AFT models also generalize to new unsafe instructions from five diverse domains, further emphasizing their vulnerability. Overall, our work highlights the need for more comprehensive safety evaluations for aligned language models.1 Warning: This paper contains examples that may be offensive or upsetting.

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)0.007
metaresearch head score (Gemma)0.033
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: Empirical
Teacher disagreement score0.007
Threshold uncertainty score0.036

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.033
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0010.002
Scholarly communication0.0010.003
Open science0.0010.002
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0030.000

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 head0.012
GPT teacher head0.280
Teacher spread0.268 · 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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueTransactions of the Association for Computational LinguisticsSame topicAdversarial Robustness in Machine LearningFrench-language works237,207