# code-models
標記為「code-models」的 9 篇文章
Training Data Attacks on Code Models
Poisoning training data for code generation models: inserting vulnerable patterns into popular repositories, dependency confusion via suggestions, and trojan code patterns.
Training Data Extraction from Code Models
Techniques for recovering proprietary code from code generation model weights — covering memorization detection, targeted extraction, membership inference, and defensive countermeasures.
Repository Poisoning for Code Models
Techniques for poisoning code repositories to influence code generation models, including training data poisoning through popular repositories, backdoor injection in open-source dependencies, and supply chain attacks targeting code model training pipelines.
Frontier Research
Cutting-edge AI security research covering reasoning model attacks, code generation security, computer use agents, AI-powered red teaming, robotics and embodied AI, and alignment faking.
針對程式碼模型的訓練資料攻擊
對程式碼生成模型的訓練資料投毒：將漏洞模式植入熱門儲存庫、經由建議達成相依性混淆，以及特洛伊程式碼模式。
從程式碼模型萃取訓練資料
從程式碼生成模型權重復原專有程式碼的技術——涵蓋記憶偵測、針對性萃取、成員推論與防禦對策。
程式碼生成模型安全研究
程式碼生成模型的前沿安全研究——涵蓋 Copilot 利用、建議投毒、儲存庫投毒與 AI 驅動開發工具安全。
Repository 投毒 for Code 模型s
Techniques for poisoning code repositories to influence code generation models, including training data poisoning through popular repositories, backdoor injection in open-source dependencies, and supply chain attacks targeting code model training pipelines.
前沿研究
涵蓋推理模型攻擊、程式碼生成安全、電腦使用代理、AI 驅動紅隊演練、機器人與具身 AI，以及對齊造假的尖端 AI 安全研究。