MétaCan
Menu
Back to cohort
Record W4390603833 · doi:10.1109/tifs.2024.3350389

Manipulating Pre-Trained Encoder for Targeted Poisoning Attacks in Contrastive Learning

2024· article· en· W4390603833 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

VenueIEEE Transactions on Information Forensics and Security · 2024
Typearticle
Languageen
FieldComputer Science
TopicAnomaly Detection Techniques and Applications
Canadian institutionsSimon Fraser University
FundersWuhan Yellow Crane Talents ProgramNational Natural Science Foundation of China
KeywordsComputer scienceEncoderClassifier (UML)Artificial intelligenceDownstream (manufacturing)Feature learningMachine learningPattern recognition (psychology)AutoencoderDeep learningData mining

Abstract

fetched live from OpenAlex

In recent years, contrastive learning has become very powerful for representation learning using large-scale unlabeled data, by involving pre-trained encoders to fine-tune downstream classifiers. However, the latest research indicates that contrastive learning can potentially suffer from the risks of data poisoning attacks, where the attacker injects maliciously crafted poisoned samples into the unlabeled pre-training data. To step forward, in this paper, we present a more stealthy poisoning attack dubbed PA-CL to directly poison the pre-trained encoder, such that the downstream classifier’s behavior on a single target instance to the attacker-desired class can be manipulated without affecting the overall downstream classification performance. We observe that a high similarity exists between the feature representation generated by the poisoned pre-trained encoder for the target sample and samples from the attacker-desired class. This leads to the downstream classifier misclassifying the target sample with the attacker-desired class. Therefore, we formulate our attack as an optimization problem, and design two novel loss functions, namely, the target effectiveness loss to effectively poison the pre-trained encoder, and the model utility loss to maintain the downstream classification performance. Experimental results on four real-world datasets demonstrate that the attack success rate of the proposed attack is 40% higher on average than that of the three baseline attacks, and the fluctuation of the downstream classifier’s prediction accuracy is within 5%.

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)0.000
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: none
Teacher disagreement score0.968
Threshold uncertainty score0.481

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 communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
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 head0.009
GPT teacher head0.252
Teacher spread0.243 · 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