Boxin Wang

Improving Certified Robustness via Statistical Learning with Logical Reasoning

2020 · arXiv (Cornell University)

Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently. However, current robustness certification methods are only able to certify under a limited perturbation radius. Given …

T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack

2019 · arXiv (Cornell University)

Adversarial attacks against natural language processing systems, which perform seemingly innocuous modifications to inputs, can induce arbitrary mistakes to the target models. Though raised great concerns, such adversarial attacks can be leveraged to estimate the …

InfoBERT: Improving Robustness of Language Models from An Information\n Theoretic Perspective

2020 · arXiv (Cornell University)

Large-scale language models such as BERT have achieved state-of-the-art\nperformance across a wide range of NLP tasks. Recent studies, however, show\nthat such BERT-based models are vulnerable facing the threats of textual\nadversarial attacks. We aim to address …

Revisit Systematic Generalization via Meaningful Learning

2020 · arXiv (Cornell University)

Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to optimistic …