上下文感知的模糊测试用于深度学习模型的鲁棒性增强
Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models
AI总结：
针对深度学习模型鲁棒性增强，提出基于上下文置信度指标的模糊测试技术Clover，通过考虑周围样本和种子间差异生成对抗样本，以提升测试-重训练流水线的有效性。
摘要：
在用于增强深度学习（DL）模型鲁棒性属性的测试-重训练流水线中，许多最先进的面向鲁棒性的模糊测试技术都是基于指标的。该流水线通过此类DL测试技术生成对抗样本作为测试用例，并使用包含这些测试用例的测试套件对被测DL模型进行重训练。一方面，这些模糊测试技术的策略紧密整合了其测试指标的关键特征。另一方面，它们通常不知道其生成的测试用例是否与围绕这些测试用例的样本不同，以及在生成当前测试用例时是否存在其他种子的相关测试用例。我们提出了一种新颖的测试指标，称为上下文置信度（CC）。CC通过测试用例周围样本的平均预测概率（针对该测试用例的预测标签）来衡量测试用例。基于该指标，我们进一步提出了一种新颖的模糊测试技术Clover，作为该流水线的DL测试技术。在每轮模糊测试中，Clover首先找到一组种子，其标签与正在模糊测试的种子的标签相同。同时，它定位在这组种子中每个种子的现有测试用例中实现最高CC值且与正在模糊测试的种子的现有测试用例（实现最高CC值）共享相同预测标签的相应测试用例。Clover计算每对这样的种子和测试用例之间的差异片段。它逐步应用这些差异片段来扰动正在模糊测试的种子的当前测试用例（实现最高CC值），并沿梯度扰动所得样本，以为正在模糊测试的种子生成新的测试用例。
英文摘要：
In the testing-retraining pipeline for enhancing the robustness property of deep learning (DL) models, many state-of-the-art robustness-oriented fuzzing techniques are metric-oriented. The pipeline generates adversarial examples as test cases via such a DL testing technique and retrains the DL model under test with test suites that contain these test cases. On the one hand, the strategies of these fuzzing techniques tightly integrate the key characteristics of their testing metrics. On the other hand, they are often unaware of whether their generated test cases are different from the samples surrounding these test cases and whether there are relevant test cases of other seeds when generating the current one. We propose a novel testing metric called Contextual Confidence (CC). CC measures a test case through the surrounding samples of a test case in terms of their mean probability predicted to the prediction label of the test case. Based on this metric, we further propose a novel fuzzing technique Clover as a DL testing technique for the pipeline. In each fuzzing round, Clover first finds a set of seeds whose labels are the same as the label of the seed under fuzzing. At the same time, it locates the corresponding test case that achieves the highest CC values among the existing test cases of each seed in this set of seeds and shares the same prediction label as the existing test case of the seed under fuzzing that achieves the highest CC value. Clover computes the piece of difference between each such pair of a seed and a test case. It incrementally applies these pieces of differences to perturb the current test case of the seed under fuzzing that achieves the highest CC value and to perturb the resulting samples along the gradient to generate new test cases for the seed under fuzzing.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
