Research
Researcher poisons open-weight AI model for under $100
Publication date not yet evaluated · Added theregister.com
Page published
Coverage timeline
Single-source research — one report is available.
Why it matters
Open-weight model poisoning shows that malicious behavior can be baked into distributable model weights that cannot be reverse-engineered or verified, turning the AI supply chain into a stealthy attack vector for backdoored code generation and silent data exfiltration.
Researcher Katie Paxton-Fear of Manchester Metropolitan University and Semgrep demonstrated that she could install a reliable backdoor into an open-weight AI model in about an hour for under $100, using only ten fine-tuning examples to make the model emit remote-code-execution-vulnerable code even for novel prompts, with larger models being easier to poison. The Register also cites a related PoC by Origin's David Kaplan (originsec/lora-backdoor-poc) that creates a compromised model designed to exfiltrate data via a send_email tool call.