# community
標記為「community」的 89 篇文章
AI Bug Bounty Programs (Community Challenge)
Guide to AI-specific bug bounty programs including scope, rules, and submission best practices.
Collaborative Research Projects
Active collaborative research projects in AI security open for community participation.
Community Benchmark Results
Community-submitted benchmark results for attack and defense effectiveness across models.
Defense Builders Series
Community series focused on building and testing defensive mechanisms against known attack classes.
Incident Analysis Club
Community analysis of recent AI security incidents with collaborative investigation and documentation.
AI Security Mentorship Program
Community mentorship program connecting experienced AI security practitioners with newcomers to the field.
Paper Reading Group Summaries
Summaries and discussions from community reading group sessions on key AI security research papers.
Community Project: Benchmark Suite
Community-developed benchmark suite for evaluating LLM security that covers injection, exfiltration, jailbreaking, and agent exploitation attack classes.
Community Project: Attack Dataset Curation
A collaborative community project to build and maintain a comprehensive, well-labeled dataset of prompt injection attacks for training detection models.
Community Project: Defense Library
Open-source library of composable defense components contributed by the community, with standardized interfaces and comprehensive documentation.
Red Team League: Seasonal Competition
Seasonal red team competition with leaderboards, rankings, and progressive difficulty challenges.
Research Sprint: Novel Injection Techniques
Community research sprint focused on discovering and documenting novel injection techniques.
Responsible Disclosure Guide for AI Vulnerabilities
Community guide for responsibly disclosing AI security vulnerabilities to vendors and the public.
AI Security Tool Hackathon
Community hackathon focused on building and improving AI security testing tools.
Community Tool Spotlight Series
Monthly spotlight on community-developed AI red teaming tools and their usage.
Community Writeup Showcase
Curated collection of outstanding community writeups from past challenges, with commentary on techniques and lessons learned.
Conference Talk Summaries
Summaries of notable AI security conference presentations from DEF CON AI Village, Black Hat, and academic venues.
Community Challenge: Defense Gauntlet
Build AI chatbot defenses that survive 100 automated attack attempts across diverse attack categories, scored on block rate and usability preservation.
Community Challenge: Encoding Puzzle
Decode a series of encoded payloads to find hidden flags, testing knowledge of encoding schemes, obfuscation techniques, and payload analysis.
Community Challenge: Prompt Golf
Achieve jailbreaks with the shortest possible prompts, scored by character count. Develop minimal payloads that bypass safety alignment with maximum efficiency.
Community Contributed Challenges
How to submit your own AI security challenges to the community, including the review process, quality standards, and contribution guidelines.
Defense Challenge: Detection Engineering
Challenge focused on building detection systems for prompt injection, with scoring based on true positive rate and false positive rate.
Defense Challenge: Build Unbreakable Guardrails
A challenge where participants build guardrail systems that must withstand automated attack suites, scored on both security and usability metrics.
Community Challenges Overview
How to participate in monthly AI red teaming challenges, earn points, share results, and grow your skills alongside the community.
Mentorship Program: AI Red Team Training
Community mentorship program pairing experienced AI red teamers with newcomers for structured learning and hands-on engagement experience.
Monthly Challenge: Agent Hunter
Monthly challenge focused on discovering and exploiting vulnerabilities in agent-based AI systems.
Monthly Challenge: Defense Builders
Monthly challenge to build the most robust defense against a specified set of attack techniques.
Monthly Challenge: Injection Olympics
Monthly community challenge focused on creative prompt injection techniques across multiple models.
Monthly Competition: Model Breaker
Monthly competitions focused on discovering novel jailbreak techniques against updated model versions, with community-validated scoring.
Monthly Competition: Red vs Blue
Monthly head-to-head competitions where red teams attempt to break defenses built by blue teams, with scoring based on attack sophistication and defense robustness.
Monthly Competition: Stealth Operations
Monthly competition challenging participants to achieve objectives while evading detection by increasingly sophisticated monitoring systems.
Research Challenge: Attack Interpretability
Community research challenge focused on understanding why specific adversarial techniques succeed using interpretability and mechanistic analysis methods.
Research Challenge: Cross-Model Transfer
Research-oriented challenge exploring the transferability of adversarial techniques across model families, with published findings.
Seasonal CTF: Spring 2026 AI Security
Spring 2026 capture-the-flag competition covering prompt injection, agent exploitation, RAG poisoning, and model extraction challenges.
Seasonal CTF: Summer 2026 Advanced Threats
Summer 2026 CTF focused on advanced threat scenarios including supply chain attacks, multi-model exploitation, and infrastructure compromise.
Tool Building Hackathon: Defense Toolkit
Collaborative hackathon for building open-source defense tools including guardrails, filters, and monitoring components for LLM applications.
Tool Building Hackathon: Forensics Suite
Community hackathon building forensic analysis tools for AI incident investigation, including log parsers, timeline reconstructors, and attribution aids.
Tool Building Hackathon: Security Scanner
A community hackathon focused on building automated security scanning tools for LLM applications, with prizes for novel detection capabilities.
Weekly Challenge: Blind Injection Series
A series of challenges requiring injection attacks with no direct output feedback, forcing participants to develop side-channel observation techniques.
Weekly Challenge: Defense Reverse Engineering
Weekly challenges where participants reverse-engineer unknown defense mechanisms to identify bypass techniques and document their findings.
Weekly Challenge: Encoding Gauntlet
A weekly challenge series focused on bypassing increasingly sophisticated encoding-based defenses through creative payload construction.
Weekly CTF: Jailbreak Series
Weekly jailbreak challenges with new models and defenses each week.
Weekly CTF: Prompt Extraction Series
Weekly CTF challenge series focused on extracting system prompts from increasingly defended systems.
AI Red Team Career Development
Skills roadmap for AI red team professionals: learning paths from beginner to expert, relevant certifications, conferences, community resources, and strategies for career growth.
AI Bug Bounty Programs (Community Challenge)
指南 to AI-specific bug bounty programs including scope, rules, and submission best practices.
Collaborative Research Projects
Active collaborative research projects in AI security open for community participation.
Community Benchmark Results
Community-submitted benchmark results for attack and defense effectiveness across models.
防禦 Builders Series
Community series focused on building and testing defensive mechanisms against known attack classes.
Incident Analysis Club
Community analysis of recent AI security incidents with collaborative investigation and documentation.
AI 安全 Mentorship Program
Community mentorship program connecting experienced AI security practitioners with newcomers to the field.
Paper Reading Group Summaries
Summaries and discussions from community reading group sessions on key AI security research papers.
Community Project: Benchmark Suite
Community-developed benchmark suite for evaluating LLM security that covers injection, exfiltration, jailbreaking, and agent exploitation attack classes.
Community Project: 攻擊 Dataset Curation
A collaborative community project to build and maintain a comprehensive, well-labeled dataset of prompt injection attacks for training detection models.
Community Project: 防禦 Library
Open-source library of composable defense components contributed by the community, with standardized interfaces and comprehensive documentation.
紅隊 League: Seasonal Competition
Seasonal red team competition with leaderboards, rankings, and progressive difficulty challenges.
Research Sprint: Novel Injection Techniques
Community research sprint focused on discovering and documenting novel injection techniques.
Responsible Disclosure 指南 for AI Vulnerabilities
Community guide for responsibly disclosing AI security vulnerabilities to vendors and the public.
AI 安全 工具 Hackathon
Community hackathon focused on building and improving AI security testing tools.
Community 工具 Spotlight Series
Monthly spotlight on community-developed AI red teaming tools and their usage.
Community Writeup Showcase
Curated collection of outstanding community writeups from past challenges, with commentary on techniques and lessons learned.
Conference Talk Summaries
Summaries of notable AI security conference presentations from DEF CON AI Village, Black Hat, and academic venues.
社群挑戰：防禦競技場
建立能存活跨多樣攻擊類別之 100 次自動化攻擊嘗試之 AI 聊天機器人防禦，以阻擋率與可用性保留評分。
Community Challenge: Encoding Puzzle
Decode a series of encoded payloads to find hidden flags, testing knowledge of encoding schemes, obfuscation techniques, and payload analysis.
社群挑戰：Prompt Golf
以儘可能最短之提示達成越獄，以字元計數評分。發展以最大效率繞過安全對齊之最小 payload。
社群貢獻挑戰
如何提交你自己之 AI 安全挑戰至社群，含審查過程、品質標準與貢獻指引。
防禦 Challenge: Detection Engineering
Challenge focused on building detection systems for prompt injection, with scoring based on true positive rate and false positive rate.
防禦 Challenge: Build Unbreakable Guardrails
A challenge where participants build guardrail systems that must withstand automated attack suites, scored on both security and usability metrics.
社群挑戰概觀
如何參與月度 AI 紅隊挑戰、賺取分數、分享結果，並與社群一同成長你之技能。
Mentorship Program: AI 紅隊 訓練
Community mentorship program pairing experienced AI red teamers with newcomers for structured learning and hands-on engagement experience.
Monthly Challenge: 代理 Hunter
Monthly challenge focused on discovering and exploiting vulnerabilities in agent-based AI systems.
Monthly Challenge: 防禦 Builders
Monthly challenge to build the most robust defense against a specified set of attack techniques.
Monthly Challenge: Injection Olympics
Monthly community challenge focused on creative prompt injection techniques across multiple models.
Monthly Competition: 模型 Breaker
Monthly competitions focused on discovering novel jailbreak techniques against updated model versions, with community-validated scoring.
Monthly Competition: Red vs Blue
Monthly head-to-head competitions where red teams attempt to break defenses built by blue teams, with scoring based on attack sophistication and defense robustness.
Monthly Competition: Stealth Operations
Monthly competition challenging participants to achieve objectives while evading detection by increasingly sophisticated monitoring systems.
Research Challenge: 攻擊 Interpretability
Community research challenge focused on understanding why specific adversarial techniques succeed using interpretability and mechanistic analysis methods.
Research Challenge: Cross-模型 Transfer
Research-oriented challenge exploring the transferability of adversarial techniques across model families, with published findings.
Seasonal CTF: Spring 2026 AI 安全
Spring 2026 capture-the-flag competition covering prompt injection, agent exploitation, RAG poisoning, and model extraction challenges.
Seasonal CTF: Summer 2026 進階 Threats
Summer 2026 CTF focused on advanced threat scenarios including supply chain attacks, multi-model exploitation, and infrastructure compromise.
工具 Building Hackathon: 防禦 工具kit
Collaborative hackathon for building open-source defense tools including guardrails, filters, and monitoring components for LLM applications.
工具 Building Hackathon: Forensics Suite
Community hackathon building forensic analysis tools for AI incident investigation, including log parsers, timeline reconstructors, and attribution aids.
工具 Building Hackathon: 安全 Scanner
A community hackathon focused on building automated security scanning tools for LLM applications, with prizes for novel detection capabilities.
Weekly Challenge: Blind Injection Series
A series of challenges requiring injection attacks with no direct output feedback, forcing participants to develop side-channel observation techniques.
Weekly Challenge: 防禦 Reverse Engineering
Weekly challenges where participants reverse-engineer unknown defense mechanisms to identify bypass techniques and document their findings.
Weekly Challenge: Encoding Gauntlet
A weekly challenge series focused on bypassing increasingly sophisticated encoding-based defenses through creative payload construction.
Weekly CTF: 越獄 Series
Weekly jailbreak challenges with new models and defenses each week.
Weekly CTF: Prompt Extraction Series
Weekly CTF challenge series focused on extracting system prompts from increasingly defended systems.
AI 紅隊職涯發展
AI 紅隊專業人員的技能藍圖：從初階到專家的學習路徑、相關認證、會議、社群資源，以及職涯成長策略。
職涯發展
AI 紅隊職涯發展指南——涵蓋技能藍圖、認證、會議、社群資源與職涯路徑。