no code implementations • ICML 2020 • Haonan Duan, Saeed Nejati, George Trimponias, Pascal Poupart, Vijay Ganesh
Our solvers out-perform the baselines by solving 12 more instances from the SAT competition 2018 application benchmark and are %40 faster on average in solving hard cryptographic instances.
no code implementations • 4 Apr 2024 • Chunxiao Li, Charlie Liu, Jonathan Chung, Zhengyang Lu, Piyush Jha, Vijay Ganesh
In most solvers, variable activities are preserved across restart boundaries, resulting in solvers continuing to search parts of the assignment tree that are not far from the one immediately prior to a restart.
1 code implementation • 30 Jan 2024 • Zhengyang Lu, Stefan Siemer, Piyush Jha, Joel Day, Florin Manea, Vijay Ganesh
Our method treats strategy synthesis as a sequential decision-making process, whose search tree corresponds to the strategy space, and employs MCTS to navigate this vast search space.
no code implementations • 24 Jan 2024 • Piyush Jha, Zhengyu Li, Zhengyang Lu, Curtis Bright, Vijay Ganesh
We perform an extensive comparison of AlphaMapleSAT against the March CnC solver on challenging combinatorial problems such as the minimum Kochen-Specker and Ramsey problems.
no code implementations • 11 Jun 2023 • Prithwish Jana, Piyush Jha, Haoyang Ju, Gautham Kishore, Aryan Mahajan, Vijay Ganesh
Also, built upon CodeT5, CoTran achieves +11. 23%, +14. 89% improvement on FEqAcc and +4. 07%, +8. 14% on CompAcc for Java-to-Python and Python-to-Java translation resp.
1 code implementation • 21 May 2023 • Piyush Jha, Joseph Scott, Jaya Sriram Ganeshna, Mudit Singh, Vijay Ganesh
We present a novel tool BertRLFuzzer, a BERT and Reinforcement Learning (RL) based fuzzer aimed at finding security vulnerabilities for Web applications.
no code implementations • 4 Apr 2023 • Vineel Nagisetty, Laura Graves, Guanting Pan, Piyush Jha, Vijay Ganesh
This functionality sets CGDTest apart from other similar DNN testing tools since it allows users to specify logical constraints to test DNNs not only for $\ell_p$ ball-based adversarial robustness but, more importantly, includes richer properties such as disguised and flow adversarial constraints, as well as adversarial robustness in the NLP domain.
no code implementations • 26 Jan 2023 • Matt Fredrikson, Kaiji Lu, Saranya Vijayakumar, Somesh Jha, Vijay Ganesh, Zifan Wang
Recent techniques that integrate \emph{solver layers} into Deep Neural Networks (DNNs) have shown promise in bridging a long-standing gap between inductive learning and symbolic reasoning techniques.
no code implementations • 7 Jul 2022 • Dhananjay Ashok, Vineel Nagisetty, Christopher Srinivasa, Vijay Ganesh
We present a novel hybrid algorithm for training Deep Neural Networks that combines the state-of-the-art Gradient Descent (GD) method with a Mixed Integer Linear Programming (MILP) solver, outperforming GD and variants in terms of accuracy, as well as resource and data efficiency for both regression and classification tasks.
no code implementations • 15 May 2021 • Murphy Berzish, Joel D. Day, Vijay Ganesh, Mitja Kulczynski, Florin Manea, Federico Mora, Dirk Nowotka
Designing an algorithm for the (generally undecidable) satisfiability problem for systems of string constraints requires a thorough understanding of the structure of constraints present in the targeted cases.
1 code implementation • 8 Dec 2020 • Curtis Bright, Kevin K. H. Cheung, Brett Stevens, Ilias Kotsireas, Vijay Ganesh
In 1989, computer searches by Lam, Thiel, and Swiercz experimentally resolved Lam's problem from projective geometry$\unicode{x2014}$the long-standing problem of determining if a projective plane of order ten exists.
no code implementations • 21 Oct 2020 • Dhananjay Ashok, Joseph Scott, Sebastian Wetzel, Maysum Panju, Vijay Ganesh
Our method, logic-guided genetic algorithm (LGGA), takes as input a set of labelled data points and auxiliary truths (ATs) (mathematical facts known a priori about the unknown function the regressor aims to learn) and outputs a specially generated and curated dataset that can be used with any SR method.
no code implementations • 21 Oct 2020 • Laura Graves, Vineel Nagisetty, Vijay Ganesh
In this paper, we present two efficient methods that address this question of how a model owner or data holder may delete personal data from models in such a way that they may not be vulnerable to model inversion and membership inference attacks while maintaining model efficacy.
no code implementations • 5 Jun 2020 • Joseph Scott, Maysum Panju, Vijay Ganesh
We introduce Logic Guided Machine Learning (LGML), a novel approach that symbiotically combines machine learning (ML) and logic solvers with the goal of learning mathematical functions from data.
no code implementations • 9 Mar 2020 • Sebastian J. Wetzel, Roger G. Melko, Joseph Scott, Maysum Panju, Vijay Ganesh
It turns out that in the process of learning which datapoints belong to the same event or field configuration, these SNNs also learn the relevant symmetry invariants and conserved quantities.
1 code implementation • 24 Feb 2020 • Vineel Nagisetty, Laura Graves, Joseph Scott, Vijay Ganesh
A potential weakness in GANs is that it requires a lot of data for successful training and data collection can be an expensive process.
1 code implementation • 1 Nov 2019 • William Zhang, Sebastian Banescu, Leodardo Pasos, Steven Stewart, Vijay Ganesh
We have implemented our technique in a tool called MPro, a scalable and automated smart contract analyzer based on the existing symbolic analysis tool Mythril-Classic and the static analysis tool Slither.
Cryptography and Security
1 code implementation • 12 Sep 2019 • Yannik Potdevin, Dirk Nowotka, Vijay Ganesh
In this paper, we propose a scientific evaluation methodology aimed at assessing the quality, efficacy, robustness and efficiency of randomized defenses to protect DNNs against adversarial examples.
no code implementations • 9 Jul 2019 • Curtis Bright, Ilias Kotsireas, Vijay Ganesh
By combining the search power of SAT with the deep mathematical knowledge in CASs we can solve many problems in mathematics that no other known methods seem capable of solving.
no code implementations • 14 Jun 2019 • Curtis Bright, Jürgen Gerhard, Ilias Kotsireas, Vijay Ganesh
In this article we demonstrate how to solve a variety of problems and puzzles using the built-in SAT solver of the computer algebra system Maple.
no code implementations • 26 Jun 2017 • Edward Zulkoski, Ruben Martins, Christoph Wintersteiger, Robert Robere, Jia Liang, Krzysztof Czarnecki, Vijay Ganesh
Over the years complexity theorists have proposed many structural parameters to explain the surprising efficiency of conflict-driven clause-learning (CDCL) SAT solvers on a wide variety of large industrial Boolean instances.
1 code implementation • 17 Jun 2015 • Jia Hui Liang, Vijay Ganesh, Venkatesh Raman, Krzysztof Czarnecki
We discovered that a key reason why large real-world FMs are easy-to-analyze is that the vast majority of the variables in these models are unrestricted, i. e., the models are satisfiable for both true and false assignments to such variables under the current partial assignment.