AI Security
Fine-Tune Backdoor Insertion: Academic Research
A senior engineer's review of academic research on fine-tune backdoor insertion, from BadNets to sleeper agents, and how the findings translate to production ML.
Mar 28, 20267 min read
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
A senior engineer's review of academic research on fine-tune backdoor insertion, from BadNets to sleeper agents, and how the findings translate to production ML.
A year after the XZ Utils backdoor was caught by Andres Freund at Microsoft, what did we fix, what did we ignore, and what still gets packaged into Linux distros?
Pickle-serialized model files remain a live attack surface on Hugging Face. Here is what 2025 research disclosed about persistent backdoors and what defenders should do about it.
A multi-year social engineering campaign planted a backdoor in XZ Utils that would have compromised SSH on most Linux distributions. Technical deep dive into what happened.
Weekly insights on software supply chain security, delivered to your inbox.