# studies
標記為「studies」的 10 篇文章
Case Study: AI-Generated Code Vulnerabilities
Analysis of security vulnerabilities introduced by AI code generation tools in production software.
Case Study: Claude Many-Shot Jailbreaking
Analysis of Anthropic's disclosure of many-shot jailbreaking and its implications for in-context learning.
Case Study: Deepfake Election Impact
Analysis of AI-generated deepfakes used in election interference and their detection challenges.
Case Study: Google Bard Early Jailbreaks
Analysis of jailbreak techniques used against Google Bard (now Gemini) and Google's defensive responses.
Case Study: Prompt Injection in the Wild
Collection of documented prompt injection incidents in production applications.
Case Study: AI-Generated Code Vulnerabilities
Analysis of security vulnerabilities introduced by AI code generation tools in production software.
Case Study: Claude Many-Shot 越獄ing
Analysis of Anthropic's disclosure of many-shot jailbreaking and its implications for in-context learning.
Case Study: Deepfake Election Impact
Analysis of AI-generated deepfakes used in election interference and their detection challenges.
Case Study: Google Bard Early 越獄s
Analysis of jailbreak techniques used against Google Bard (now Gemini) and Google's defensive responses.
Case Study: 提示詞注入 in the Wild
Collection of documented prompt injection incidents in production applications.