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

Junyu Ren

2 indexed papers

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

Publications per year

2
26

Top categories

Stats ML×1AI×1ML×1Optimization and Control×1Crypto×1

Frequent co-authors

Ziwei Su1×
Victor Veitch1×
Xingjian Pan1×
Wensheng Gan1×
Philip S. Yu1×

Research Timeline

2026
DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection

The paper introduces PromptFuzz-SC, a novel semantic-character dual-space mutation framework, demonstrating that combining both semantic and character-level attacks significantly improves the robustness evaluation of LLMs like DeepSeek against prompt injection.

Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms

This paper explains how discarded norms in contrastive embedding models correlate with semantic properties and provides a theoretical framework.

Highlighted terms show continued research focus across papers

Papers

stat.MLcs.AIcs.LGTheoreticalRecentJun 29, 2026

Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms

Ziwei Su, Junyu Ren, Victor Veitch

This paper explains how discarded norms in contrastive embedding models correlate with semantic properties and provides a theoretical framework.

View →
cs.CRRecentApr 14, 2026

DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection

Junyu Ren, Xingjian Pan, Wensheng Gan, Philip S. Yu

The paper introduces PromptFuzz-SC, a novel semantic-character dual-space mutation framework, demonstrating that combining both semantic and character-level attacks significantly improves the robustne…

View →