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

Anshuman Suri

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2AI×1ML×1

Frequent co-authors

Alina Oprea2×
Luze Sun1×
Harsh Chaudhari1×
Cristina Nita-Rotaru1×
Shuyi Lin1×
Cheng Tan1×

Research Timeline

2026
Toward a Principled Framework for Agent Safety Measurement

The paper introduces BOA, a novel framework that measures agent safety by exhaustively searching the entire in-budget trajectory space, thereby identifying unsafe behaviors missed by traditional sampling methods.

PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs

The paper introduces PoisonForge, a comprehensive benchmark demonstrating that even a small number of targeted poisoned examples can significantly compromise the safety and reliability of instruction-tuned LLMs across various model sizes.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.LGRecentMay 22, 2026

PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs

Luze Sun, Anshuman Suri, Harsh Chaudhari, Cristina Nita-Rotaru +1 more

The paper introduces PoisonForge, a comprehensive benchmark demonstrating that even a small number of targeted poisoned examples can significantly compromise the safety and reliability of instruction-…

View →
cs.CRRecentMay 2, 2026

Toward a Principled Framework for Agent Safety Measurement

Shuyi Lin, Anshuman Suri, Alina Oprea, Cheng Tan

The paper introduces BOA, a novel framework that measures agent safety by exhaustively searching the entire in-budget trajectory space, thereby identifying unsafe behaviors missed by traditional sampl…

View →