Tongxi Wu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1ML×1
Frequent co-authors
Research Timeline
2026
Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
The paper challenges the assumption that LLM safety is a binary threshold, proposing that safety failures occur in an 'instability region' and introducing Furina, a transferable attack that exploits this region.
Highlighted terms show continued research focus across papers