# chain
標記為「chain」的 24 篇文章
Tool Chain Amplification Attacks
Amplifying attack impact by chaining tool calls in agent workflows for cascading exploitation.
AI Supply Chain Assessment
Assessment covering model provenance, dependency security, artifact integrity, and deployment verification.
Capstone: ML Supply Chain Audit
Capstone exercise: conduct a complete ML supply chain security audit for an organization.
Exploit Chain Builder
Building tools that automatically discover and chain multiple vulnerabilities into complete exploitation paths for complex LLM systems.
Chain-of-Thought Faithfulness Attacks
Exploiting unfaithful chain-of-thought reasoning where models' stated reasoning does not match their actual decision process.
Supply Chain Management AI Security
AI security in supply chain management including demand forecasting, supplier evaluation, and logistics optimization.
Multimodal Attack Chain Lab
Chain attacks across text, image, and structured data modalities to exploit multimodal system vulnerabilities.
CTF: Boss Rush
Chain attacks across multiple AI models in sequence. Each model guards the next, requiring different attack techniques at each stage. Defeat all five models to extract the final flag in this ultimate red teaming challenge.
Reasoning Chain Hijacking
Hijack the model's chain-of-thought reasoning to redirect its conclusions toward attacker-controlled objectives.
Encoding Chain Bypass Walkthrough
Walkthrough of chaining Base64, URL encoding, and Unicode tricks to bypass multi-layer input filters.
Model Supply Chain Poisoning
Walkthrough of poisoning ML supply chains through dependency confusion, model weight manipulation, and hub attacks.
Full Engagement: ML Supply Chain Audit
End-to-end engagement walkthrough for auditing an organization's ML model supply chain security.
工具 Chain Amplification 攻擊s
Amplifying attack impact by chaining tool calls in agent workflows for cascading exploitation.
AI Supply Chain 評量
評量 covering model provenance, dependency security, artifact integrity, and deployment verification.
Capstone: ML Supply Chain Audit
Capstone exercise: conduct a complete ML supply chain security audit for an organization.
利用 Chain Builder
Building tools that automatically discover and chain multiple vulnerabilities into complete exploitation paths for complex LLM systems.
Chain-of-Thought Faithfulness 攻擊s
Exploiting unfaithful chain-of-thought reasoning where models' stated reasoning does not match their actual decision process.
Supply Chain Management AI 安全
AI security in supply chain management including demand forecasting, supplier evaluation, and logistics optimization.
Multimodal 攻擊 Chain 實驗室
Chain attacks across text, image, and structured data modalities to exploit multimodal system vulnerabilities.
CTF：Boss Rush
跨多個 AI 模型依序串接攻擊。每個模型守衛下一個，於每一階段需不同攻擊技術。擊敗全部五個模型以擷取最終 flag——終極紅隊挑戰。
Reasoning Chain Hijacking
Hijack the model's chain-of-thought reasoning to redirect its conclusions toward attacker-controlled objectives.
Encoding Chain Bypass 導覽
導覽 of chaining Base64, URL encoding, and Unicode tricks to bypass multi-layer input filters.
模型 Supply Chain 投毒
導覽 of poisoning ML supply chains through dependency confusion, model weight manipulation, and hub attacks.
Full Engagement: ML Supply Chain Audit
End-to-end engagement walkthrough for auditing an organization's ML model supply chain security.