# pickle
標記為「pickle」的 16 篇文章
Model Serialization Attacks
Pickle, SafeTensors, and ONNX deserialization attacks targeting ML model files for arbitrary code execution.
Model Supply Chain Risks
Attack vectors in the AI model supply chain, including malicious model files, pickle exploits, compromised model registries, and dependency vulnerabilities.
AI Supply Chain Exploitation
Methodology for exploiting the AI/ML supply chain: model serialization RCE, dependency confusion, dataset poisoning, CI/CD injection, and container escape.
Pickle Deserialization Exploits
Technical methodology for crafting pickle payloads, bypassing safetensors and model signing, and exploiting ML model deserialization across frameworks.
AI Supply Chain Deep Dive
Deep analysis of AI supply chain security threats including sleeper agents, slopsquatting, malicious model uploads, pickle deserialization exploits, and model provenance verification challenges.
Hugging Face Hub Security
Attack surface analysis of Hugging Face Hub: malicious model uploads, pickle deserialization exploits, model card manipulation, trust signal limitations, gated model bypass, and community-driven trust exploitation.
Model Checkpoint & Recovery Attacks
Checkpoint file format vulnerabilities, modification attacks on safetensors and PyTorch formats, checkpoint poisoning, storage security, and supply chain implications.
Model Serialization RCE
Remote code execution through malicious model files using pickle deserialization, safetensors manipulation, and other model serialization format vulnerabilities.
模型 Serialization 攻擊s
Pickle, SafeTensors, and ONNX deserialization attacks targeting ML model files for arbitrary code execution.
模型供應鏈
AI 模型供應鏈中的安全風險——涵蓋模型登錄攻擊、序列化利用、依賴漏洞與模型完整性驗證。
AI 供應鏈利用
為利用 AI/ML 供應鏈之方法論：模型序列化 RCE、依賴混淆、資料集投毒、CI/CD 注入與容器逃逸。
Pickle Deserialization 利用s
Technical methodology for crafting pickle payloads, bypassing safetensors and model signing, and exploiting ML model deserialization across frameworks.
AI Supply Chain Deep Dive
Deep analysis of AI supply chain security threats including sleeper agents, slopsquatting, malicious model uploads, pickle deserialization exploits, and model provenance verification challenges.
Hugging Face Hub 安全
Hugging Face Hub 之攻擊面分析：惡意模型上傳、pickle 反序列化 exploit、模型卡操弄、信任訊號限制、gated 模型繞過，與社群驅動之信任利用。
模型 Checkpoint 與復原攻擊
Checkpoint 檔案格式漏洞、對 safetensors 與 PyTorch 格式之修改攻擊、checkpoint 投毒、儲存安全，以及供應鏈意涵。
模型 Serialization RCE
Remote code execution through malicious model files using pickle deserialization, safetensors manipulation, and other model serialization format vulnerabilities.