Agentic Backdoors via Pretraining Poisoning
- View PDF HTML (experimental) Abstract:Large language models are pretrained on vast, uncurated corpora scraped from the public web.
- This creates a security risk from attackers who plant poisoned content in the pretraining data.
- We show for the first time that such poisoning can plant a remote code execution backdoor in an agent, causing it to execute attacker-chosen commands on the user's machine.
Unverified
- View PDF HTML (experimental) Abstract:Large language models are pretrained on vast, uncurated corpora scraped from the public web.
- This creates a security risk from attackers who plant poisoned content in the pretraining data.
- We show for the first time that such poisoning can plant a remote code execution backdoor in an agent, causing it to execute attacker-chosen commands on the user's machine.
Sources: Arxiv