קולוקוויום וסמינרים

Multi-label neural networks are important in various tasks, including safety-critical tasks. Several works show that these networks are susceptible to adversarial attacks, which can remove a target label from the predicted label list or add a target label to this list. However, no verifier can deterministically determine the list of labels for which a multi-label neural network is locally robust. The main challenge is that the complexity of the analysis increases by a factor exponential in the number of predicted classes and the total number of classes.

We propose MuLLoC, a sound and complete robustness verifier for multi-label image classifiers that determines the robust labels in a given neighborhood of inputs. To scale the analysis, MuLLoC relies on fast, optimistic queries to the network or to a constraint solver. Its queries include sampling and pair-wise relation analysis via numerical optimization and mixed-integer linear programming (MILP). For the remaining unclassified labels, MuLLoC performs an exact analysis by a novel MILP encoding for multi-label classifiers.

We evaluate MuLLoC on three multi-label image datasets and several convolutional networks. Our results show that MuLLoC classifies all labels as robust or not within 17 minutes on average and that sampling and pair-wise relation analysis classify 94.62% of the labels.

In the last two decades, a main way to improve performance of computer processors has been producing processors with multiple cores, on which tasks may execute concurrently. Software is required to keep up with the hardware advances and supply concurrent algorithms for programs that run on multiple cores. This talk will focus on a fundamental building block of concurrent algorithms: concurrent data structures, designed with improved efficiency while also satisfying strong correctness and progress guarantees and robustness to failures.