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

Jianwei Li

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2AI×2ML×2

Frequent co-authors

Jung-Eun Kim2×

Research Timeline

2026
Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation

The paper argues that the 'positive backdoor' label should be retired and replaced with 'Secret Alignment,' asserting that all such protective claims require rigorous, standardized evaluation due to inherent brittleness.

Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation

The paper argues that the 'positive backdoor' label should be retired and replaced with 'Secret Alignment,' asserting that such protective claims must be rigorously evaluated for security, especially concerning confidentiality, integrity, and availability.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.LGRecentMay 27, 2026

Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation

Jianwei Li, Jung-Eun Kim

The paper argues that the 'positive backdoor' label should be retired and replaced with 'Secret Alignment,' asserting that all such protective claims require rigorous, standardized evaluation due to i…

View →
cs.CRcs.AIcs.LGRecentMay 27, 2026

Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation

Jianwei Li, Jung-Eun Kim

The paper argues that the 'positive backdoor' label should be retired and replaced with 'Secret Alignment,' asserting that such protective claims must be rigorously evaluated for security, especially…

View →