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

Pin-Yu Chen

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2ML×1NLP×1AI×1

Frequent co-authors

Daniel Yiming Cao1×
Chengzhong Wang1×
Sheng-Yen Chou1×
Chengyu Huang1×
Shengwei An1×
Xinjie Shen1×

Research Timeline

2026
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue

The paper introduces TurnGate, a response-aware defense mechanism that detects the earliest turn in a multi-turn dialogue where the accumulated interaction enables a harmful action, significantly improving malicious intent detection.

Backdooring Masked Diffusion Language Models

The paper introduces SHADOWMASK, the first systematic backdoor attack targeting Masked Diffusion Language Models (MDLMs), demonstrating near-100% attack success while preserving clean model utility.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CRRecentMay 19, 2026

Backdooring Masked Diffusion Language Models

Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou, Chengyu Huang +2 more

The paper introduces SHADOWMASK, the first systematic backdoor attack targeting Masked Diffusion Language Models (MDLMs), demonstrating near-100% attack success while preserving clean model utility.

View →
cs.CLcs.AIcs.CRRecentMay 7, 2026

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue

Xinjie Shen, Rongzhe Wei, Peizhi Niu, Haoyu Wang +5 more

The paper introduces TurnGate, a response-aware defense mechanism that detects the earliest turn in a multi-turn dialogue where the accumulated interaction enables a harmful action, significantly impr…

View →