Research map / Learning theory and algorithms / Submodular and game algorithms
Manipulating a Learning Defender and Ways to Counteract
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use the optimal EoP-maximizing policy instead of the SSE policy | defender in Stackelberg security games · random games with zero-sum attacker type included in type set | EoP | Helped |
| use the QR (quantal response) heuristic policy instead of the SSE policy | defender in Stackelberg security games · random games with zero-sum attacker type included in type set | EoP | Helped |
| use the optimal policy instead of the SSE policy | defender in Stackelberg security games · purely random attacker types, varying rho and game size | EoP | No clear effect |
Closest papers by meaning
- Behavioral Learning in Security Games: Threat of Multi-Step Manipulative Attacks (AAAI 2023 · similarity 0.90)
- Learning Optimal Strategies to Commit To (AAAI 2019 · similarity 0.90)
- Optimal Attack and Defense for Reinforcement Learning (AAAI 2024 · similarity 0.89)
- Regret Minimization in Stackelberg Games with Side Information (NeurIPS 2024 · similarity 0.85)
- Strategic Classification With Externalities (ICLR 2025 · similarity 0.85)
- Safe Exploitative Play with Untrusted Type Beliefs (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.