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

Wei Yang Bryan Lim

2 indexed papers

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

Publications per year

2
26

Top categories

AI×2Crypto×2Vision×1NLP×1ML×1

Frequent co-authors

Xinyu Yan1×
Boyang Chen1×
Jiaming Zhang1×
Tiantong Wu1×
Hong Xi Tae1×
Yichen He1×

Research Timeline

2026
Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

The paper proposes SALO, a novel detector that monitors the dynamic, layer-wise activation pattern (Refusal Trajectory) to improve jailbreak detection robustness compared to traditional methods relying on static terminal representations.

FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence

The paper introduces FraudBench, a multimodal benchmark designed to detect AI-generated fraudulent refund evidence, finding that current AI models struggle significantly with claim-conditioned fake-damage detection.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.CRRecentMay 9, 2026

FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence

Xinyu Yan, Boyang Chen, Jiaming Zhang, Tiantong Wu +11 more

The paper introduces FraudBench, a multimodal benchmark designed to detect AI-generated fraudulent refund evidence, finding that current AI models struggle significantly with claim-conditioned fake-da…

View →
cs.CRcs.AIcs.CLRecentMay 2, 2026

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

Xulin Hu, Che Wang, Wei Yang Bryan Lim, Jianbo Gao +1 more

The paper proposes SALO, a novel detector that monitors the dynamic, layer-wise activation pattern (Refusal Trajectory) to improve jailbreak detection robustness compared to traditional methods relyin…

View →