Research map / Bandits and online learning / Multi-armed bandits
When to Reset Your Keys: Optimal Timing of Security Updates via Learning
Zizhan Zheng, Ness Shroff, Prasant Mohapatra
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 side observations to eliminate shorter defense periods while playing the longest active period | Finite-period optimal timing · Synthetic Weibull attacks, binary and linear loss | long-term regret | Improved |
| Use the more aggressive elimination threshold 4c_m instead of the standard threshold (ablation) | TUCB-improved-side · Synthetic Weibull attacks | long-term regret | Improved |
| Use side observations after choosing arms with TUCB (ablation) | TUCB · Synthetic Weibull attacks, binary and linear loss | long-term regret | No clear effect |
Closest papers by meaning
- Optimal Attack and Defense for Reinforcement Learning (AAAI 2024 · similarity 0.85)
- PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent (ICML 2026 · similarity 0.82)
- Dynamic Risk Assessments for Offensive Cybersecurity Agents (NeurIPS 2025 · similarity 0.82)
- MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs (AAAI 2026 · similarity 0.81)
- Adapting to Evolving Adversaries with Regularized Continual Robust Training (ICML 2025 · similarity 0.81)
- Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL (ICLR 2024 · similarity 0.81)
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.
