Research

ML Security, Privacy, Fairness

• Sanjari Srivastava, Piotr Mardziel, Zhikhun Zhang, Archana Ahlawat, Anupam Datta, John C Mitchell. De-amplifying Bias from Differential Privacy in Language Model Fine-tuning. In AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI). 2024.
• Kaiji Lu, Piotr Mardziel, Fangjing Wu, Preetam Amancharla, Anupam Datta. Gender Bias in Neural Natural Language Processing. In Logic, Language, and Security: Essays Dedicated to Andre Scedrov on the Occasion of His 65th Birthday. 2020.
• Zifan Wang, Haofan Wang, Shakul Ramkumar, Matthew Fredrikson, Piotr Mardziel, Anupam Datta. Smoothed Geometry for Robust Attribution. In Neural Information Processing Systems (NeurIPS). 2020.
• Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover. An Information-Theoretic Quantification of Discrimination with Exempt Features. In Conference on Artificial Intelligence (AAAI). 2020.
• Anupam Datta, Matthew Fredrikson, Gihyuk Ko, Piotr Mardziel, Shayak Sen. Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs. In Conference on Computer & Communications Security (CCS). 2017.

ML Interpretability

• Kaiji Lu, Piotr Mardziel, Klas Leino, Matthew Fredrikson, Anupam Datta. Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models. In Annual Meeting of the Association for Computational Linguistics (ACL). 2020.
• Zifan Wang, Piotr Mardziel, Anupam Datta, Matthew Fredrikson. Interpreting Interpretations: Organizing Attribution Methods by Criteria. In CVPR Workshop on Fair, Data Efficient and Trusted Computer Vision. 2020.
• Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel, Xia Hu. Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks. In CVPR Workshop on Fair, Data Efficient and Trusted Computer Vision. 2020.

Security and Privacy

• José Manuel Calderón Trilla, Michael Hicks, Stephen Magill, Piotr Mardziel, Ian Sweet. Probabilistic Abstract Interpretation: Sound Inference and Application to Privacy. In Foundations of Probabilistic Programming, Cambridge University Press. 2020.
• James Parker, Michael Hicks, Andrew Ruef, Michelle Mazurek, Dave Levin, Daniel Votipka, Piotr Mardziel, Kelsey Fulton. Build It, Break It, Fix It: Contesting Secure Development. In ACM Transactions on Privacy and Security (TOPS). 2020.
• Mario Alvim, Piotr Mardziel, Michael Hicks. Quantifying vulnerability of secret generation using hyper-distributions. In International Conference on Principles of Security and Trust (POST). 2017.
• Andrew Ruef, Michael Hicks, James Parker, Dave Levin, Michelle Mazurek, Piotr Mardziel. Build It, Break It, Fix It: Contesting Secure Development. In Conference on Computer & Communications Security (CCS). 2016.
• Mario Alvim, Piotr Mardziel, Michael Hicks. Towards the Quantification of Strategy Leakage. In Workshop on Foundations of Computer Security (FCS). 2016.
• MHR Khouzani, Piotr Mardziel, Carlos Cid, Mudhakar Srivatsa. Picking vs. Guessing Secrets: A Game-Theoretic Analysis. In Computer Security Foundations Symposium (CSF). 2015.
• Andrew Ruef, Michael Hicks, James Parker, Dave Levin, Atif Memon, Jandelyn Plane, Piotr Mardziel. Build It Break It: Measuring and Comparing Development Security. In Workshop on Cyber Security Experimentation and Test (CSET). 2015.
• Piotr Mardziel, Mario Alvim, Michael Hicks, Michael Clarkson. Quantifying Information Flow for Dynamic Secrets. In Symposium on Security and Privacy (S&P/Oakland). 2014.
• Piotr Mardziel, Mario Alvim, Michael Hicks. Adversary Gain vs. Defender Loss in Quantified Information Flow. In Workshop on Foundations of Computer Security (FCS). 2014.
• Piotr Mardziel, Stephen Magill, Michael Hicks, Mudhakar Srivatsa. Dynamic Enforcement of Knowledge-based Security Policies using Probabilistic Abstract Interpretation. In Journal of Computer Security (JCS). 2013.
• Aseem Rastogi, Piotr Mardziel, Matthew Hammer, Michael Hicks. Knowledge Inference for Optimizing Secure Multi-party Computation. In Workshop on Programming Languages and Analysis of Security (PLAS). 2013.
• Piotr Mardziel, Michael Hicks, Jonathan Katz, Mudhakar Srivatsa. Knowledge-Oriented Secure Multiparty Computation. In Workshop on Programming Languages and Analysis of Security (PLAS). 2012.
• Piotr Mardziel, Stephen Magill, Michael Hicks, Mudhakar Srivatsa. Dynamic Enforcement of Knowledge-based Security Policies. In Computer Security Foundations Symposium (CSF). 2011.

Static (and Probabilistic) Analysis

• José Manuel Calderón Trilla, Michael Hicks, Stephen Magill, Piotr Mardziel, Ian Sweet. Probabilistic Abstract Interpretation: Sound Inference and Application to Privacy. In Foundations of Probabilistic Programming, Cambridge University Press. 2020.
• Shiyi Wei, Piotr Mardziel, Andrew Ruef, Jeffrey S. Foster, Michael Hicks. Evaluating Design Tradeoffs in Numeric Static Analysis for Java. In European Symposium on Programming (ESOP). 2018.
• Piotr Mardziel, Stephen Magill, Michael Hicks, Mudhakar Srivatsa. Dynamic Enforcement of Knowledge-based Security Policies using Probabilistic Abstract Interpretation. In Journal of Computer Security (JCS). 2013.
• Piotr Mardziel, Michael Hicks, Jonathan Katz, Mudhakar Srivatsa. Knowledge-Oriented Secure Multiparty Computation. In Workshop on Programming Languages and Analysis of Security (PLAS). 2012.
• Piotr Mardziel, Stephen Magill, Michael Hicks, Mudhakar Srivatsa. Dynamic Enforcement of Knowledge-based Security Policies. In Computer Security Foundations Symposium (CSF). 2011.