Introduces a two-stage robust optimization model with decision-dependent uncertainty sets to capture evolving manipulation costs and reduce gaming in strategic classification.
arXiv preprint arXiv:2007.10457 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.
citing papers explorer
-
Robust Strategic Classification under Decision-Dependent Cost Uncertainty
Introduces a two-stage robust optimization model with decision-dependent uncertainty sets to capture evolving manipulation costs and reduce gaming in strategic classification.
-
Insider Attacks in Multi-Agent LLM Consensus Systems
A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.