Guiding dynamic programing via structural probability for accelerating programming by example

R Ji, Y Sun, Y Xiong, Z Hu - Proceedings of the ACM on Programming …, 2020 - dl.acm.org
Programming by example (PBE) is an important subproblem of program synthesis, and PBE
techniques have been applied to many domains. Though many techniques for accelerating …

Overfitting in synthesis: Theory and practice

S Padhi, T Millstein, A Nori, R Sharma - International Conference on …, 2019 - Springer
In syntax-guided synthesis (SyGuS), a synthesizer's goal is to automatically generate a
program belonging to a grammar of possible implementations that meets a logical …

Search-based local black-box deobfuscation: understand, improve and mitigate

G Menguy, S Bardin, R Bonichon, CS Lima - Proceedings of the 2021 …, 2021 - dl.acm.org
Code obfuscation aims at protecting Intellectual Property and other secrets embedded into
software from being retrieved. Recent works leverage advances in artificial intelligence (AI) …

Generalizable synthesis through unification

R Ji, J Xia, Y Xiong, Z Hu - Proceedings of the ACM on Programming …, 2021 - dl.acm.org
The generalizability of PBE solvers is the key to the empirical synthesis performance.
Despite the importance of generalizability, related studies on PBE solvers are still limited. In …

Ai-based blackbox code deobfuscation: Understand, improve and mitigate

G Menguy, S Bardin, R Bonichon, CS Lima - arXiv preprint arXiv …, 2021 - arxiv.org
Code obfuscation aims at protecting Intellectual Property and other secrets embedded into
software from being retrieved. Recent works leverage advances in artificial intelligence with …

LLM Meets Bounded Model Checking: Neuro-symbolic Loop Invariant Inference

G Wu, W Cao, Y Yao, H Wei, T Chen, X Ma - Proceedings of the 39th …, 2024 - dl.acm.org
Loop invariant inference, a key component in program verification, is a challenging task due
to the inherent undecidability and complex loop behaviors in practice. Recently, machine …

Decomposition-Based Synthesis for Applying Divide-and-Conquer-Like Algorithmic Paradigms

R Ji, Y Zhao, Y Xiong, D Wang, L Zhang… - ACM Transactions on …, 2024 - dl.acm.org
Algorithmic paradigms such as divide-and-conquer (D&C) are proposed to guide
developers in designing efficient algorithms, but it can still be difficult to apply algorithmic …

On Scaling Data-Driven Loop Invariant Inference

S Bhatia, S Padhi, N Natarajan, R Sharma… - arXiv preprint arXiv …, 2019 - arxiv.org
Automated synthesis of inductive invariants is an important problem in software verification.
Once all the invariants have been specified, software verification reduces to checking of …

Occam Learning Meets Synthesis Through Unification

R Ji, J Xia, Y Xiong, Z Hu - arXiv preprint arXiv:2105.14467, 2021 - arxiv.org
The generalizability of PBE solvers is the key to the empirical synthesis performance.
Despite the importance of generalizability, related studies on PBE solvers are still limited. In …

[PDF][PDF] Black-Box Algorithm Synthesis

R Ji, Y Xiong, Z Hu - jiry17.github.io
Algorithm synthesis is a newly emerging branch of program synthesis, targeting to
automatically apply a predefined class of algorithms to a user-provided program. In …