Unverified50% confidenceFactExact time
Large model security attack methods are typically classified by access level into black-box attacks, gray-box attacks, and white-box attacks.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAdversarial attacks have evolved into multiple schools, including white-box attacks (such as FGSM and PGD) and black-box attacks.73% similarUnverified攻击面是网络安全领域指系统中所有可能被攻击者利用的入口点总和的概念，通常分为网络攻击面、软件攻击面和人员攻击面三类72% similarUnverifiedData poisoning attacks are categorized into types such as Clean-Label Attacks and Trojan Attacks.72% similarUnverifiedAnthropic's cybersecurity safeguards target scenarios involving the prevention of models being misused to generate malicious code, plan attack vectors, or assist in launching cyberattacks against critical infrastructure.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/922737API
curl https://kongchang.com/api/v1/knowledge/claims/922737MCP
get_claim(id=922737)