BestHub
Sign in
Tag

model safety

1 views collected around this technical thread.

Data Thinking Notes
Data Thinking Notes
May 13, 2025 · Information Security

DeepSeek Security: Top 5 Model Threats and How to Defend

This report examines DeepSeek’s security and reliability by detailing five core model threats—DDoS attacks, unlimited inference, vulnerability exploitation, data poisoning, and jailbreak—alongside two private‑deployment risks and three external threats such as counterfeit apps, offering targeted mitigation strategies to help users safely adopt the platform.

AI securityDeepSeeklarge language model
0 likes · 8 min read
DeepSeek Security: Top 5 Model Threats and How to Defend
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Jan 3, 2024 · Artificial Intelligence

Llama 2: Open Foundation and Fine‑Tuned Chat Models – Ghost Attention, RLHF Results, and Safety Evaluation

This article summarizes the Llama 2 series, describing the Ghost Attention technique for maintaining system‑message consistency across multi‑turn dialogs, presenting RLHF and human evaluation results, and discussing extensive safety pre‑training, benchmark assessments, and model release details.

AI evaluationGhost AttentionLlama 2
0 likes · 20 min read
Llama 2: Open Foundation and Fine‑Tuned Chat Models – Ghost Attention, RLHF Results, and Safety Evaluation