Yuliang Yan
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1NLP×1ML×1
Frequent co-authors
Research Timeline
2026
Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
The paper introduces R$^2$A, an adversarial attack that uses suffix optimization to mislead black-box LLM routers into consistently selecting expensive, high-capability models.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIcs.CLRecentApr 16, 2026
Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
Haochun Tang, Yuliang Yan, Jiahua Lu, Huaxiao Liu +1 more
The paper introduces R$^2$A, an adversarial attack that uses suffix optimization to mislead black-box LLM routers into consistently selecting expensive, high-capability models.
View →