--- title: "Somesh Jha — author profile and papers — Elamur Research" description: "Somesh Jha, Google: 2 papers on Elamur Research (2017–2026), h-index 71 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/somesh-jha/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/somesh-jha/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Somesh Jha # Somesh Jha Somesh Jha has 2 papers in our library, in 2017–2026; often with [Matt Fredrikson](https://md.research.elamur.ai/free/en/authors/matt-fredrikson/), [Mihai Christodorescu](https://md.research.elamur.ai/free/en/authors/mihai-christodorescu/), [Varun Chandrasekaran](https://md.research.elamur.ai/free/en/authors/varun-chandrasekaran/). 2 papers in our library · 2017–2026 [OpenAlex](https://openalex.org/A5088826068) · [ORCID](https://orcid.org/0000-0001-5877-0436) · [Wikidata](https://www.wikidata.org/wiki/Q130952978) · [**h-index 71**](https://openalex.org/authors/A5088826068) · [355 works](https://openalex.org/works?filter=author.id:A5088826068) · [32,496 citations](https://openalex.org/works?filter=author.id:A5088826068&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/somesh-jha/#papers) · [🔗 Cited 119 times in our library](https://md.research.elamur.ai/free/en/authors/somesh-jha/cited-by/) · [9 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #2411](https://md.research.elamur.ai/free/en/paper-stars/page/25/#star-2411) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Somesh+Jha) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Somesh+Jha) · [dblp](https://dblp.org/search?q=Somesh+Jha) · [ACL Anthology](https://aclanthology.org/search/?q=Somesh+Jha) ## Affiliations [🎓**University of Wisconsin–Madison** Madison · United States 2000–2026 · 217 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-wisconsin-madison/) · [🏢**Google** Mountain View · United States 2023–2026 · 2 papers*current*](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**Carnegie Mellon University** Pittsburgh · United States 1992–2002 · 25 papers](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🎓**University of Wisconsin System** Madison · United States 2001–2023 · 21 papers](https://ror.org/03ydkyb10) · [🎓**Pennsylvania State University** State College · United States 1991–2016 · 3 papers](https://md.research.elamur.ai/free/en/universities/pennsylvania-state-university/) · [🎓**University of California, Berkeley** Berkeley · United States 2010–2020 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) · [🔬**SRI International** Menlo Park · United States 2018–2019 · 2 papers](https://md.research.elamur.ai/free/en/labs/sri-international/) · [🔬**IMDEA Software Institute** Pozuelo de Alarcón · Spain 2016 · 2 papers](https://ror.org/04xvfkh51) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 7 The field of science this work belongs to (OpenAlex fields).[Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Sociology and Political Science · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 💡 Concepts 1 Key ideas and methods explained on our concept pages.[Machine learning · 1 work](https://md.research.elamur.ai/free/en/concepts/machine-learning/) ## Works by year ### 2020s [**2026** 1 paper](https://md.research.elamur.ai/free/en/authors/somesh-jha/year/2026/) ### 2010s [**2017** 1 paper](https://md.research.elamur.ai/free/en/authors/somesh-jha/year/2017/) ## Papers The most cited first (OpenAlex and our library). 1. **[Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting](https://md.research.elamur.ai/free/en/papers/yeom-2017-privacy-risk-machine-learning-analyzing/)** *(2017 · 1,036 citations)* Models trained on sensitive records can expose facts about the people in their training sets. Before this work, the causes of that leakage were explained mostly through scattered anecdotes. Yeom, Giacomelli, Fredrikson and Jha study two black-box threats. Membership inference asks whether a given record was used for… 2. **[SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification](https://md.research.elamur.ai/free/en/papers/zhou-2026-sactor-llm-driven-correct-idiomatic/)** *(2026 · 1 citation)* Moving legacy C code to Rust can remove whole classes of memory bugs. Rule-based converters such as C2Rust produce Rust that leans heavily on unsafe , and plain LLM prompting gives no assurance that the result behaves like the original. SACTOR addresses both problems. A libclang-based C Parser splits a program into… ## All works 11 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them. 1. [**Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting arXiv:1709.01604**Samuel Yeom, Irene Giacomelli, Matt Fredrikson, et al.*2017 · 1,036 citations*](https://md.research.elamur.ai/free/en/papers/yeom-2017-privacy-risk-machine-learning-analyzing/) 2. **[Towards automatic generation of vulnerability-based signatures ↗](https://doi.org/10.1109/sp.2006.41) Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · no summary yet**David Brumley et al.*2006 · 297 citations* 3. **[Creating Vulnerability Signatures Using Weakest Preconditions ↗](https://doi.org/10.1109/csf.2007.17) Proceedings - Computer Security Foundations Workshop/Proceedings · no summary yet**David Brumley et al.*2007 · 89 citations* 4. **[Identifying and Mitigating the Security Risks of Generative AI ↗](https://doi.org/10.1561/3300000041) Foundations and Trends® in Privacy and Security · no summary yet**Clark Barrett et al.*2023 · 79 citations* 5. **[SoK: Watermarking for AI-Generated Content ↗](https://doi.org/10.1109/sp61157.2025.00178) Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · no summary yet**Xuandong Zhao et al.*2025 · 33 citations* 6. **[Malware Detection ↗](https://doi.org/10.1007/978-0-387-44599-1) Advances in information security · no summary yet**Mihai Christodorescu et al.*2007 · 29 citations* 7. **[Theory and Techniques for Automatic Generation of Vulnerability-Based Signatures ↗](https://doi.org/10.1109/tdsc.2008.55) IEEE Transactions on Dependable and Secure Computing · no summary yet**David Brumley et al.*2008 · 28 citations* 8. **[Theory and Techniques for Automatic Generation of Vulnerability-Based Signatures ↗](https://doi.org/10.21236/ada462599) no summary yet**David Brumley et al.*2006 · 12 citations* 9. **[Malware Detection (Advances in Information Security) ↗](https://openalex.org/W2463752017) Springer eBooks · no summary yet**Mihai Christodorescu et al.*2006 · 7 citations* 10. **[PolicyLR: A Logic Representation For Privacy Policies ↗](https://arxiv.org/abs/2408.14830) arXiv:2408.14830 · no summary yet**Ashish Hooda et al.*2024 · 2 citations* 11. **[SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification](https://md.research.elamur.ai/free/en/papers/zhou-2026-sactor-llm-driven-correct-idiomatic/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Tianyang Zhou, Ziyi Zhang, Haowen Lin, et al.*2026 · 1 citation* ## Co-authors here 3 co-authors with a page, the most papers together first. - [Matt Fredrikson](https://md.research.elamur.ai/free/en/authors/matt-fredrikson/) - [Mihai Christodorescu](https://md.research.elamur.ai/free/en/authors/mihai-christodorescu/) - [Varun Chandrasekaran](https://md.research.elamur.ai/free/en/authors/varun-chandrasekaran/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy ×2 - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/): [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) - Advances in information security - Foundations and Trends® in Privacy and Security - IEEE Transactions on Dependable and Secure Computing - Proceedings - Computer Security Foundations Workshop/Proceedings - Springer eBooks ## Cited by Papers of our library cite their works 119 times (of the 149,439 papers whose bibliographies we read); [29 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/somesh-jha/cited-by/). Updated 1 November 2026