Re:The Demonization of DeepSeek: How NIST Turned Open Scienc...
by arw0n on Monday October 06, 2025 @09:15AM
(#45491062)
The biggest and most difficult to mitigate attack vector is indirect prompt injection.[0] So far most case studies have been injecting malicious prompts at inference, but there is good reason to believe you can do this effectively at different stages of training as well.[1] By layering obfuscation techniques, these become very hard to detect.
[0] https://arxiv.org/abs/2302.12173
[1] https://arxiv.org/html/2410.14827v3