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

Farinaz Koushanfar

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2AI×1NLP×1ML×1

Frequent co-authors

Samuel Breckenridge1×
Dani Vilardell1×
Derek Leung1×
Andrés Fábrega1×
James Austgen1×
Ari Juels1×

Research Timeline

2026
LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning

The paper introduces Adaptive Unlearning (AU), a post-deployment framework that surgically suppresses code-related hallucinations, significantly reducing the risk of package confusion attacks like slopsquatting.

$π$Creds: Privately Inferred Credentials

The paper introduces $\pi$Creds, a novel system for generating privacy-preserving, decentralized verifiable credentials by leveraging LLM inference over authenticated data, significantly expanding the types of claims that can be certified.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentJun 2, 2026

$π$Creds: Privately Inferred Credentials

Samuel Breckenridge, Dani Vilardell, Derek Leung, Andrés Fábrega +3 more

The paper introduces $\pi$Creds, a novel system for generating privacy-preserving, decentralized verifiable credentials by leveraging LLM inference over authenticated data, significantly expanding the…

View →
cs.CRcs.AIcs.CLRecentMay 1, 2026

LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning

Joseph Spracklen, Pedram Aghazadeh, Farinaz Koushanfar, Murtuza Jadliwala

The paper introduces Adaptive Unlearning (AU), a post-deployment framework that surgically suppresses code-related hallucinations, significantly reducing the risk of package confusion attacks like slo…

View →