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

Traian Rebedea

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

NLP×4Crypto×3AI×2

Frequent co-authors

Yoshinari Fujinuma2×
Varun Gangal2×
Makesh Narasimhan Sreedhar2×
Prasoon Varshney2×
Rebecca Qian2×
Anand Kannappan2×

Research Timeline

2026
Training a General Purpose Automated Red Teaming Model

The paper proposes a general-purpose pipeline to train automated red teaming models capable of generating attacks for arbitrary adversarial goals, overcoming the limitations of current methods that are restricted to safety and content moderation.

"Înţelegi Româneşte?'' A Recipe for Romanian Vision-Language Models

This paper details the systematic construction and training of a high-performing Romanian Vision-Language Model (VLM), demonstrating that language-specific adaptation significantly boosts performance over general models.

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents

This paper proposes and evaluates guardian-based defenses, both dynamic and static, to mitigate skill injection attacks targeting LLM agents that rely on reusable procedural skills.

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents

This paper introduces and evaluates guardian-based defenses, showing that an intermediary LLM agent can significantly reduce the success rate of skill injection attacks on terminal-based agents, even when attacks are reframed.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.CLRecentJun 1, 2026

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents

Yoshinari Fujinuma, Varun Gangal, Traian Rebedea, Makesh Narasimhan Sreedhar +3 more

This paper proposes and evaluates guardian-based defenses, both dynamic and static, to mitigate skill injection attacks targeting LLM agents that rely on reusable procedural skills.

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

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents

Yoshinari Fujinuma, Varun Gangal, Traian Rebedea, Makesh Narasimhan Sreedhar +3 more

This paper introduces and evaluates guardian-based defenses, showing that an intermediary LLM agent can significantly reduce the success rate of skill injection attacks on terminal-based agents, even…

View →
cs.CLRecentMay 29, 2026

"Înţelegi Româneşte?'' A Recipe for Romanian Vision-Language Models

Mihai Masala, Marius Leordeanu, Mihai Dascalu, Traian Rebedea

This paper details the systematic construction and training of a high-performing Romanian Vision-Language Model (VLM), demonstrating that language-specific adaptation significantly boosts performance…

View →
cs.CRcs.CLRecentApr 24, 2026

Training a General Purpose Automated Red Teaming Model

Aishwarya Padmakumar, Leon Derczynski, Traian Rebedea, Christopher Parisien

The paper proposes a general-purpose pipeline to train automated red teaming models capable of generating attacks for arbitrary adversarial goals, overcoming the limitations of current methods that ar…

View →