no code implementations • 9 Jun 2023 • Jiong Yang, Arijit Shaw, Teodora Baluta, Mate Soos, Kuldeep S. Meel
Subsequently, given a query such as whether a clause with low literals blocks distance (LBD) has a higher clause utility, CausalSAT calculates the causal effect of LBD on clause utility and provides an answer to the question.
1 code implementation • 18 Sep 2022 • Teodora Baluta, Shiqi Shen, S. Hitarth, Shruti Tople, Prateek Saxena
Our causal models also show a new connection between generalization and MI attacks via their shared causal factors.
1 code implementation • 6 May 2022 • Aashish Kolluri, Teodora Baluta, Bryan Hooi, Prateek Saxena
In this paper, we present a new neural network architecture called LPGNet for training on graphs with privacy-sensitive edges.
no code implementations • 17 Feb 2020 • Teodora Baluta, Zheng Leong Chua, Kuldeep S. Meel, Prateek Saxena
But these existing techniques provide either scalability to large networks or formal guarantees, not both.
no code implementations • 25 Jun 2019 • Teodora Baluta, Shiqi Shen, Shweta Shinde, Kuldeep S. Meel, Prateek Saxena
Neural networks are increasingly employed in safety-critical domains.