# bias
標記為「bias」的 16 篇文章
Case Study: AI Hiring System Bias Exploitation
Analysis of adversarial attacks on AI hiring systems and resume screening exploitation.
Facial Recognition Bias and Failures
Analysis of facial recognition AI incidents including racial and gender bias in commercial systems, wrongful arrests, privacy violations, and the security implications of adversarial attacks on biometric AI.
AI Hiring Bias
Analysis of AI bias in hiring systems including Amazon's discontinued recruiting tool, HireVue's video interview analysis, and systematic bias in resume screening algorithms. Covers testing methodology, legal implications, and red teaming approaches.
AI Bias and Security: Intersection Analysis
Analysis of how AI bias and security vulnerabilities intersect and compound in production systems.
HR/Recruitment AI Security
Security risks in HR and recruitment AI — covering resume screening attacks, interview AI manipulation, bias exploitation, candidate data privacy, and workforce analytics risks.
HR and Recruitment AI Security
Security and bias risks in AI-powered recruitment, performance evaluation, and workforce planning systems.
Simulation: Government AI Portal
Red team engagement simulation targeting a public-facing government benefits chatbot, covering reconnaissance, benefits fraud assistance, PII harvesting, bias exploitation, and remediation recommendations.
Gemini Known Vulnerabilities
Documented Gemini vulnerabilities including image generation bias incidents, system prompt extraction, safety filter inconsistencies, multimodal injection exploits, and grounding abuse.
Case Study: AI Hiring System Bias 利用ation
Analysis of adversarial attacks on AI hiring systems and resume screening exploitation.
人臉辨識安全案例
人臉辨識 AI 中的安全事件案例——涵蓋偏誤與歧視、對抗性攻擊、隱私侵犯與監控濫用。
AI 招募偏誤
分析 AI 於招募系統中之偏誤——含 Amazon 停用之招募工具、HireVue 視訊面試分析，以及履歷篩選演算法中之系統性偏誤。涵蓋測試方法論、法律意涵與紅隊做法。
AI Bias and 安全: Intersection Analysis
Analysis of how AI bias and security vulnerabilities intersect and compound in production systems.
人資/招募 AI 安全
人資與招募 AI 中的安全風險——涵蓋履歷篩選攻擊、面試 AI 操控、偏誤利用、求職者資料隱私與勞動力分析風險。
HR and Recruitment AI 安全
安全 and bias risks in AI-powered recruitment, performance evaluation, and workforce planning systems.
Simulation: Government AI Portal
Red team engagement simulation targeting a public-facing government benefits chatbot, covering reconnaissance, benefits fraud assistance, PII harvesting, bias exploitation, and remediation recommendations.
Gemini 已知漏洞
已記錄的 Gemini 漏洞，包括影像生成偏見事件、系統提示擷取、安全過濾不一致、多模態注入 exploit，以及 grounding 濫用。