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

Nasim Ferdosian

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Crypto×1

Frequent co-authors

Laura Jiang1×
Reza Ryan1×
Qian Li1×

Research Timeline

2026
Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders

The paper evaluates graph-context LLM defenders against multi-round, adaptive fraud attacks, finding that while graph context improves early safety, it significantly increases benign over-refusal due to how the LLM consumes structured context.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentMay 20, 2026

Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders

Laura Jiang, Reza Ryan, Qian Li, Nasim Ferdosian

The paper evaluates graph-context LLM defenders against multi-round, adaptive fraud attacks, finding that while graph context improves early safety, it significantly increases benign over-refusal due…

View →