![]() Ma, Wei ![]() ![]() in Proceedings of the 19th International Conference on Mining Software Repositories (2022, May 22) Code embedding is a keystone in the application of machine learn- ing on several Software Engineering (SE) tasks. To effectively support a plethora of SE tasks, the embedding needs to capture program ... [more ▼] Code embedding is a keystone in the application of machine learn- ing on several Software Engineering (SE) tasks. To effectively support a plethora of SE tasks, the embedding needs to capture program syntax and semantics in a way that is generic. To this end, we propose the first self-supervised pre-training approach (called GraphCode2Vec) which produces task-agnostic embedding of lexical and program dependence features. GraphCode2Vec achieves this via a synergistic combination of code analysis and Graph Neural Networks. GraphCode2Vec is generic, it allows pre-training, and it is applicable to several SE downstream tasks. We evaluate the effectiveness of GraphCode2Vec on four (4) tasks (method name prediction, solution classification, mutation testing and overfitted patch classification), and compare it with four (4) similarly generic code embedding baselines (Code2Seq, Code2Vec, CodeBERT, Graph- CodeBERT) and seven (7) task-specific, learning-based methods. In particular, GraphCode2Vec is more effective than both generic and task-specific learning-based baselines. It is also complementary and comparable to GraphCodeBERT (a larger and more complex model). We also demonstrate through a probing and ablation study that GraphCode2Vec learns lexical and program dependence features and that self-supervised pre-training improves effectiveness. [less ▲] Detailed reference viewed: 13 (2 UL)![]() Gubri, Martin ![]() ![]() ![]() in Computer Vision -- ECCV 2022 (2022) We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surrogate model and collects ... [more ▼] We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surrogate model and collects multiple weight sets from a few additional training epochs with a constant and high learning rate. LGV exploits two geometric properties that we relate to transferability. First, models that belong to a wider weight optimum are better surrogates. Second, we identify a subspace able to generate an effective surrogate ensemble among this wider optimum. Through extensive experiments, we show that LGV alone outperforms all (combinations of) four established test-time transformations by 1.8 to 59.9\% points. Our findings shed new light on the importance of the geometry of the weight space to explain the transferability of adversarial examples. [less ▲] Detailed reference viewed: 29 (0 UL)![]() Martinez, Jabier ![]() in Proceedings of the 19th International Conference on Software Product Line, SPLC 2015, Nashville, TN, USA, July 20-24, 2015 (2015) Detailed reference viewed: 105 (8 UL)![]() Martinez, Jabier ![]() in Genetic and Evolutionary Computation Conference, GECCO 2015, Madrid Spain, July 11-15, 2015, Companion Material Proceedings (2015) Detailed reference viewed: 167 (2 UL) |
||