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

Rozhin Yasaei

3 indexed papers

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

Publications per year

3
26

Top categories

Crypto×3ML×2NLP×2

Frequent co-authors

Mohammed Sameer Syed2×
Sujan Ghimire1×
Parsa Mirfasihi1×
Muhtasim Alam Chowdhury1×
Veeramani Pugazhenthi1×
Harish Kumar Dharavath1×

Research Timeline

2026
Can Agents Secure Hardware? Evaluating Agentic LLM-Driven Obfuscation for IP Protection

This paper introduces an agentic LLM-driven framework that automates the generation of functionally correct and security-relevant hardware netlist obfuscation for protecting intellectual property.

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

The paper introduces the Safety Asymmetry Score (SAS) to measure how a model's susceptibility to adversarial attacks changes based on whether the malicious content arrives via the user message, tool metadata, or tool output, revealing systematic, channel-dependent blind spots.

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

The paper introduces the Safety Asymmetry Score (SAS) to measure how a model's vulnerability to adversarial content changes based on whether the malicious input arrives via the user message, tool metadata, or tool output, revealing systematic, channel-dependent blind spots.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CLcs.CRRecentMay 30, 2026

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

Mohammed Sameer Syed, Rozhin Yasaei

The paper introduces the Safety Asymmetry Score (SAS) to measure how a model's susceptibility to adversarial attacks changes based on whether the malicious content arrives via the user message, tool m…

View →
cs.LGcs.CLcs.CRRecentMay 30, 2026

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

Mohammed Sameer Syed, Rozhin Yasaei

The paper introduces the Safety Asymmetry Score (SAS) to measure how a model's vulnerability to adversarial content changes based on whether the malicious input arrives via the user message, tool meta…

View →
cs.CRRecentApr 14, 2026

Can Agents Secure Hardware? Evaluating Agentic LLM-Driven Obfuscation for IP Protection

Sujan Ghimire, Parsa Mirfasihi, Muhtasim Alam Chowdhury, Veeramani Pugazhenthi +5 more

This paper introduces an agentic LLM-driven framework that automates the generation of functionally correct and security-relevant hardware netlist obfuscation for protecting intellectual property.

View →