paper-with-me

홈 › Papers

Decentralized Attack Search and the Design of Bug Bounty Schemes

2023-03-31 · Hans Gersbach, Akaki Mamageishvili, Fikri Pitsuwan

Systems and blockchains often have security vulnerabilities and can be attacked by adversaries, with potentially significant negative consequences. Therefore, infrastructure providers increasingly rely on bug bounty programs, where external individuals probe the system and report any vulnerabilities (bugs) in exchange for rewards (bounty). We develop a simple contest model of bug bounty. A group of individuals of arbitrary size is invited to undertake a costly search for bugs. The individuals differ with regard to their abilities, which we capture by different costs to achieve a certain probability to find bugs if any exist. Costs are private information. We study equilibria of the contest and characterize the optimal design of bug bounty schemes. In particular, the designer can vary the size of the group of individuals invited to search, add a paid expert, insert an artificial bug with some probability, and pay multiple prizes.

📄 PDF Abstract BibTeX arXiv:2304.00077

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Artificial Bugs for Crowdsearch

2024-03-14 · Hans Gersbach, Fikri Pitsuwan, Pio Blieske

Bug bounty programs, where external agents are invited to search and report vulnerabilities (bugs) in exchange for rewards (bounty), have become a major tool for companies to improve their systems. We suggest augmenting …

Agent Hunt: Bounty Based Collaborative Autoformalization With LLM Agents

2026-03-06 · Chad E. Brown, Cezary Kaliszyk, Josef Urban arxiv

We describe an experiment in large-scale autoformalization of algebraic topology in an Interactive Theorem Proving (ITP) environment, where the workload is distributed among multiple LLM-based coding agents. Rather than …

The Current State of AI Bias Bounties: An Overview of Existing Programmes and Research

2025-10-02 · Sergej Kucenko, Nathaniel Dennler, Fengxiang He arxiv

Current bias evaluation methods rarely engage with communities impacted by AI systems. Inspired by bug bounties, bias bounties have been proposed as a reward-based method that involves communities in AI bias detection by…

Bias Detection

Byzantine-Robust Aggregation for Securing Decentralized Federated Learning

2024-09-26 · Diego Cajaraville-Aboy, Ana Fernández-Vilas, Rebeca P. Díaz-Redondo, Manuel Fernández-Veiga

Federated Learning (FL) emerges as a distributed machine learning approach that addresses privacy concerns by training AI models locally on devices. Decentralized Federated Learning (DFL) extends the FL paradigm by elimi…

Federated Learningimage-classificationImage Classification

Misalignment Bounty: Crowdsourcing AI Agent Misbehavior

2025-10-22 · Rustem Turtayev, Natalia Fedorova, Oleg Serikov, Sergey Koldyba 외 arxiv

Advanced AI systems sometimes act in ways that differ from human intent. To gather clear, reproducible examples, we ran the Misalignment Bounty: a crowdsourced project that collected cases of agents pursuing unintended o…