Xinlei He
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 1 in the filters
on a stage with
- Jingjing Wangonce
- Jingyi Zhengonce
- Lijin Wangonce
all 11 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| From Purity to Peril: Backdooring Merged Models From "Harmless" Benign... | USENIX Security '25 | 2025-08-13 |
Introduces MergeBackdoor, a two-stage training method that makes each upstream model appear clean (upstream ASRs at random-guessing level) yet causes the… | ||
| Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety... | USENIX Security '25 | 2025-08-13 |
Quantifies unsafe outputs on seven AIPSEs using URLs from PhishTank, ThreatBook, LevelBlue, testing 3 query types (keyword lists, natural language, direct URL)… | ||
| nothing matches | ||