blogs.cisco.com Evaluating Security Risk in DeepSeek and Other Frontier Reasoning Models
The performance of DeepSeek models has made a clear impact, but are these models safe and secure? We use algorithmic AI vulnerability testing to find out.
Chat about and share AI stuff
Members 150 Posts 3 Active Today 1 Created 2 yr. ago
Chat about and share AI stuff
Members
150
Posts
3
Active Today
1
Created
2 yr. ago
-
Researchers say they had a ‘100% attack success rate’ on jailbreak attempts against Chinese AI DeepSeek
cross-posted from: https://lemmy.sdf.org/post/28910537
Researchers claim they had a ‘100% attack success rate’ on jailbreak attempts against Chinese AI DeepSeek
"DeepSeek R1 was purportedly trained with a fraction of the budgets that other frontier model providers spend on developing their models. However, it comes at a different cost: safety and security," researchers say.
A research team at Cisco managed to jailbreak DeepSeek R1 with a 100% attack success rate. This means that there was not a single prompt from the HarmBench set that did not obtain an affirmative answer from DeepSeek R1. This is in contrast to other frontier models, such as o1, which blocks a majority of adversarial attacks with its model guardrails.
...
In other related news, experts are cited by CNBC that [DeepSeek’s privacy pol
-
Interstellar Documents
The interstellar beings has ask me to share this low quality YouTube video in hope of inspiring a new era of technological advancement.