Static and Sequential Malicious Attacks in the Context of Selective Forgetting
Authors: Chenxu Zhao, Wei Qian, Rex Ying, Mengdi Huai
NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We perform theoretical analyses for the proposed selective forgetting attacks, and extensive experimental results validate the effectiveness of our proposed selective forgetting attacks. The source code is available in the supplementary material. In this section, we conduct comprehensive experiments to evaluate the effectiveness of our proposed selective forgetting attacks. |
| Researcher Affiliation | Academia | Chenxu Zhao Department of Computer Science Iowa State University cxzhao@iastate.edu Wei Qian Department of Computer Science Iowa State University wqi@iastate.edu Rex Ying Department of Computer Science Yale University rex.ying@yale.edu Mengdi Huai Department of Computer Science Iowa State University mdhuai@iastate.edu |
| Pseudocode | No | The algorithm and generalization to other unlearning methods are deferred to the supplementary material. |
| Open Source Code | Yes | The source code is available in the supplementary material. |
| Open Datasets | Yes | In experiments, we adopt the following real-world datasets: CIFAR-10 [31], Adult [15], Diabetes [1], and MNIST [12]. |
| Dataset Splits | No | The paper discusses training and testing but does not explicitly provide details about validation dataset splits (e.g., percentages, sample counts, or specific methods for creating a validation set). |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions using DDPG [35] but does not specify version numbers for any software, libraries, or frameworks used in the experiments (e.g., Python, PyTorch, TensorFlow, scikit-learn versions). |
| Experiment Setup | No | Due to space limitations, a detailed description of the experimental setup, parameter settings, and more experimental results are given in the supplementary material. |