MétaCan
Menu
Back to cohort

DevilDiffusion: Embedding Hidden Noise Backdoors into Diffusion Models

2024· article· en· W4405440513 on OpenAlexaff
William Aiken, Paula Branco, Guy-Vincent Jourdan

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldDecision Sciences
TopicSimulation Techniques and Applications
Canadian institutionsUniversity of Ottawa
Fundersnot available
KeywordsComputer scienceNoise (video)EmbeddingDiffusionComputer securityArtificial intelligencePhysics

Abstract

fetched live from OpenAlex

Diffusion models represent state-of-the-art deep learning architectures behind many popular and powerful image-synthesizing generative Artificial Intelligence (AI) systems. Their underlying approach, which relies on scheduled noise addition and optimized noise removal, has been applicable to the syn-thesis of sophisticated and nearly photorealistic images across various domains; however, the potential impacts of compro-mised diffusion models remain an underexplored area in the literature. While prior studies have investigated the insertion of explicit triggers into the noise or prompt spaces of diffusion models, it is unrealistic to assume that benign users would intentionally input such triggers into their own diffusion process. In our DevilDiffusion approach, we demonstrate the capability to surreptitiously embed triggers that leverage uncommon but naturally -occurring characteristics of Gaussian noise directly into the noise space of conditional diffusion models. When these specific characteristics occur in naturally -occurring noise, the model will instead construct our target backdoor image. By adjusting the trigger size and the ratio of poisoned images, we can control the trigger rates of the specified target image, ranging from less than 0.01 % to 25 % of all generated images, while still maintaining performance on the target task.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.768
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0040.002

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 head0.103
GPT teacher head0.430
Teacher spread0.327 · 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; both teacher heads agree on what is shown here.

Study designTheoretical or conceptual
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

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicSimulation Techniques and ApplicationsFrench-language works237,207