Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Mardziel, Piotr"'
Autor:
Srivastava, Sanjari, Mardziel, Piotr, Zhang, Zhikhun, Ahlawat, Archana, Datta, Anupam, Mitchell, John C
Fairness and privacy are two important values machine learning (ML) practitioners often seek to operationalize in models. Fairness aims to reduce model bias for social/demographic sub-groups. Privacy via differential privacy (DP) mechanisms, on the o
Externí odkaz:
http://arxiv.org/abs/2402.04489
While attention is all you need may be proving true, we do not know why: attention-based transformer models such as BERT are superior but how information flows from input tokens to output predictions are unclear. We introduce influence patterns, abst
Externí odkaz:
http://arxiv.org/abs/2011.00740
Autor:
Chen, Xuan, Wang, Zifan, Fan, Yucai, Jin, Bonan, Mardziel, Piotr, Joe-Wong, Carlee, Datta, Anupam
Feature attribution has been a foundational building block for explaining the input feature importance in supervised learning with Deep Neural Network (DNNs), but face new challenges when applied to deep Reinforcement Learning (RL).We propose a new a
Externí odkaz:
http://arxiv.org/abs/2009.08507
With the growing use of ML in highly consequential domains, quantifying disparity with respect to protected attributes, e.g., gender, race, etc., is important. While quantifying disparity is essential, sometimes the needs of an occupation may require
Externí odkaz:
http://arxiv.org/abs/2006.07986
Autor:
Wang, Zifan, Wang, Haofan, Ramkumar, Shakul, Fredrikson, Matt, Mardziel, Piotr, Datta, Anupam
Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs. This lack of robustness is especially
Externí odkaz:
http://arxiv.org/abs/2006.06643
LSTM-based recurrent neural networks are the state-of-the-art for many natural language processing (NLP) tasks. Despite their performance, it is unclear whether, or how, LSTMs learn structural features of natural languages such as subject-verb number
Externí odkaz:
http://arxiv.org/abs/2005.01190
Motivated by distinct, though related, criteria, a growing number of attribution methods have been developed tointerprete deep learning. While each relies on the interpretability of the concept of "importance" and our ability to visualize patterns, e
Externí odkaz:
http://arxiv.org/abs/2002.07985
Autor:
Wang, Haofan, Wang, Zifan, Du, Mengnan, Yang, Fan, Zhang, Zijian, Ding, Sirui, Mardziel, Piotr, Hu, Xia
Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions. In this paper, we develop a novel post-hoc visual explanation method called Score-CAM
Externí odkaz:
http://arxiv.org/abs/1910.01279
Autor:
Parker, James, Hicks, Michael, Ruef, Andrew, Mazurek, Michelle L., Levin, Dave, Votipka, Daniel, Mardziel, Piotr, Fulton, Kelsey R.
Typical security contests focus on breaking or mitigating the impact of buggy systems. We present the Build-it, Break-it, Fix-it (BIBIFI) contest, which aims to assess the ability to securely build software, not just break it. In BIBIFI, teams build
Externí odkaz:
http://arxiv.org/abs/1907.01679
We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with state-of-the-art neu
Externí odkaz:
http://arxiv.org/abs/1807.11714