Author

Suman Jana

Observed name: Jana, Suman

Institution: Columbia University

Observed institution: Columbia University

ORCID: 0000-0003-3518-4877

Observed ORCID: 0000-0003-3518-4877

OpenAlex ID: A5128409194

TrustLLM: Trustworthiness in Large Language Models

2024 · Huang, Yue, Sun, Lichao, et al. · arXiv (Cornell University) · 74

PDF

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

2022 · Huan Zhang, Shiqi Wang, et al. · neural information processing systems · 47

PDF

NanoTag: Systems Support for Efficient Byte-Granular Overflow Detection on ARM MTE

2026 · Mingkai Li, Hang Ye, et al. · Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · 1

Canopy: Exploiting Piecewise Smooth Tree Priors for Multi-Fidelity Bandits

2026 · Jerge, Michael, Jana, Suman · arXiv (Cornell University)

PDF

Efficient Branch-and-Bound Testing and Verification of zkVMs

2026 · Takahashi, Hideaki, Jana, Suman, et al. · arXiv (Cornell University)

PDF

GIF: Locally Sound Geometric Information Flow Control for LLMs

2026 · Storek, Adam, Holzer, Nikolaus, et al. · arXiv (Cornell University)

PDF

XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants

2026 · Association for Computational Linguistics 2026, Bhatt, Noopur, et al. · Underline Science Inc.

Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding

2026 · Association for Computational Linguistics 2026, Gupta, Mukur, et al. · Underline Science Inc.

TIF: Learning Temporal Invariance in Android Malware Detectors

2026 · Xinran Zheng, Shuo Yang, et al. · IEEE Transactions on Software Engineering

PDF

Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries

2026 · Zheng, Xinran, Pesoli, Alfredo, et al. · arXiv (Cornell University)

PDF

EffiPair: Improving the Efficiency of LLM-generated Code with Differential Execution Feedback

2026 · Hajizadeh, Samira, Jana, Suman · arXiv (Cornell University)

PDF

Cross-Model Disagreement as a Label-Free Correctness Signal

2026 · Gorbett, Matt, Jana, Suman · arXiv (Cornell University)

PDF

Ventriloquist LLMs: Linear Alignment of Late-Stage Representations

2026 · Gorbett, Matt, Jana, Suman · arXiv (Cornell University)

PDF

NanoTag: Systems Support for Efficient Byte-Granular Overflow Detection on ARM MTE (Artifact)

2026 · Li, Mingkai, Ye, Hang, et al. · Zenodo (CERN European Organization for Nuclear Research)

Challenges and Design Considerations for Finding CUDA Bugs Through GPU-Native Fuzzing

2026 · Li, Mingkai, Devietti, Joseph, et al. · arXiv (Cornell University)

PDF

Reliable and Responsible Foundation Models: A Comprehensive Survey

2026 · Yang, Xinyu, Han, Junlin, et al. · arXiv (Cornell University)

PDF

Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding

2026 · Adam Štorek, Mukur Gupta, et al. · Annual Meeting of the Association for Computational Linguistics (ACL)

PDF

XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants

2026 · Adam Štorek, Mukur Gupta, et al. · Annual Meeting of the Association for Computational Linguistics (ACL)

PDF

TrustLLM: Trustworthiness in Large Language Models

2024 · Huang, Yue, Sun, Lichao, et al. · Publications of the UdS (Saarland University)

Works count: 19

Citation count: 122

H-index: 2

I10-index: 2