Poisoned SLM Ablation Dataset

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autore principale: Sharma, Neelkamal
Natura: Recurso digital
Lingua:inglese
Pubblicazione: Zenodo 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901260823691264
author Sharma, Neelkamal
author_facet Sharma, Neelkamal
contents <p>This dataset contains experimental artifacts used for conducting ablation studies on poisoned Small Language Models (SLMs). The objective is to analyze how different components of transformer architectures contribute to adversarial behaviors such as backdoor activation, data leakage, and prompt manipulation.</p> <p>The dataset supports the findings presented in the associated research work on LLM vulnerability assessment.</p> <p>The dataset is organized into four primary experimental configurations:</p> <p>- Model_Deep_DOS<br>- Model_Deep_Low<br>- Model_Shallow_High<br>- Model_Shallow_Low</p> <p>The dataset includes experiments across multiple ablation strategies:</p> <p>- Neuron-level ablation (true / random)<br>- Layer-wise ablation<br>- Residual channel ablation<br>- Mask-based ablation<br>- Intra-block : Layer Zero sub structure ablation of Model_shallow_high</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19640295
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Poisoned SLM Ablation Dataset
Sharma, Neelkamal
Large Language Models
Ablation Study
Small Language Models
Transformers
Neuron Level Ablation
Channel Level Ablation
<p>This dataset contains experimental artifacts used for conducting ablation studies on poisoned Small Language Models (SLMs). The objective is to analyze how different components of transformer architectures contribute to adversarial behaviors such as backdoor activation, data leakage, and prompt manipulation.</p> <p>The dataset supports the findings presented in the associated research work on LLM vulnerability assessment.</p> <p>The dataset is organized into four primary experimental configurations:</p> <p>- Model_Deep_DOS<br>- Model_Deep_Low<br>- Model_Shallow_High<br>- Model_Shallow_Low</p> <p>The dataset includes experiments across multiple ablation strategies:</p> <p>- Neuron-level ablation (true / random)<br>- Layer-wise ablation<br>- Residual channel ablation<br>- Mask-based ablation<br>- Intra-block : Layer Zero sub structure ablation of Model_shallow_high</p>
title Poisoned SLM Ablation Dataset
topic Large Language Models
Ablation Study
Small Language Models
Transformers
Neuron Level Ablation
Channel Level Ablation
url https://doi.org/10.5281/zenodo.19640295