280 citations · 1k across the 17 of their papers we have counts for
5 papers · 1 filter
Reducing Sentiment Bias in Language Models via Counterfactual Evaluation
Po-Sen Huang, Huan Zhang, Ray Jiang +6
Advances in language modeling architectures and the availability of large text corpora have driven progress in automatic text generation. While this results in models capable of ge…
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
Po-Sen Huang, Robert Stanforth, Johannes Welbl +5
Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversari…
Adversarial Robustness through Local Linearization
Chongli Qin, James Martens, Sven Gowal +6
Adversarial training is an effective methodology for training deep neural networks that are robust against adversarial, norm-bounded perturbations. However, the computational cost…
Are Labels Required for Improving Adversarial Robustness?
Jonathan Uesato, Jean-Baptiste Alayrac, Po-Sen Huang +3
Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets…
Verification of Non-Linear Specifications for Neural Networks
Chongli Qin, Krishnamurthy, Dvijotham +7
Prior work on neural network verification has focused on specifications that are linear functions of the output of the network, e.g., invariance of the classifier output under adve…