Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
Authors: Ali Shafahi, W. Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer, Tudor Dumitras, Tom Goldstein
NeurIPS 2018 | Venue PDF | LLM Run Details | Input Tokens: 15,326 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,166 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate our method by generating poisoned frog images from the CIFAR dataset and using them to manipulate image classi๏ฌers. |
| Researcher Affiliation | Academia | Ali Shafahi University of Maryland EMAIL W. Ronny Huang University of Maryland EMAIL Mahyar Najibi University of Maryland EMAIL Octavian Suciu University of Maryland EMAIL Christoph Studer Cornell University EMAIL Tudor Dumitras University of Maryland EMAIL Tom Goldstein University of Maryland EMAIL |
| Pseudocode | Yes | Algorithm 1 Poisoning Example Generation |
| Open Source Code | Yes | 2The code is available at https://github.com/ashafahi/inceptionv3-transferLearn-poison |
| Open Datasets | Yes | We used the Adam optimizer with learning rate of 0.01 to train the network for 100 epochs. |
| Dataset Splits | No | The paper provides details on training and test sets but does not explicitly mention a separate validation set split or its details. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not specify any particular software versions or dependencies required to replicate the experiment. |
| Experiment Setup | Yes | We use the Adam optimizer with learning rate of 0.01 to train the network for 100 epochs. |