Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Mihai Christodorescu

Mihai Christodorescu

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×3AI×2Software Eng.×1HCI×1

Frequent co-authors

Earlence Fernandes1×
Ashish Hooda1×
Somesh Jha1×
Johann Rehberger1×
Kamalika Chaudhuri1×
Xiaohan Fu1×

Research Timeline

2026
Uncovering Relationships between Android Developers, User Privacy, and Developer Willingness to Reduce Fingerprinting Risks

The study surveyed Android developers to assess their willingness to adopt changes that mitigate device fingerprinting risks, finding that developers overwhelmingly support privacy protections even with high effort, but prefer optional implementation.

Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning

The paper introduces LLMVD.js, a multi-stage LLM agent pipeline that effectively detects and confirms taint-style vulnerabilities in Node.js packages, achieving significantly higher confirmation rates than traditional program analysis tools.

Agent Security is a Systems Problem

The paper argues that agent security must be treated as a systems problem, requiring the enforcement of security invariants at the system level rather than solely relying on improving the underlying AI model's robustness.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 18, 2026

Agent Security is a Systems Problem

Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha +10 more

The paper argues that agent security must be treated as a systems problem, requiring the enforcement of security invariants at the system level rather than solely relying on improving the underlying A…

View →
cs.CRcs.AIcs.SERecentApr 22, 2026

Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning

Ronghao Ni, Mihai Christodorescu, Limin Jia

The paper introduces LLMVD.js, a multi-stage LLM agent pipeline that effectively detects and confirms taint-style vulnerabilities in Node.js packages, achieving significantly higher confirmation rates…

View →
cs.CRcs.HCRecentMar 30, 2026

Uncovering Relationships between Android Developers, User Privacy, and Developer Willingness to Reduce Fingerprinting Risks

Alex Berke, Güliz Seray Tuncay, Michael Specter, Mihai Christodorescu

The study surveyed Android developers to assess their willingness to adopt changes that mitigate device fingerprinting risks, finding that developers overwhelmingly support privacy protections even wi…

View →