BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models — mentioned by lmf4lol

Fri, 29 May 2026 07:32:38 GMT

This is not entirely true and ignoring a couple of potential attack vectors like Data Poisoning: https://arxiv.org/abs/2408.12798 Its of course highly dependant on the use case and the environment, but simply saying that the only important part is to know where the data goes is too simple.

Paper and discussion history. A mention is not an endorsement.

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models — mentioned by teej

Sun, 15 Dec 2024 08:21:27 GMT

It’s absolutely possible to put a backdoor into an LLM. https://arxiv.org/abs/2408.12798

Paper and discussion history. A mention is not an endorsement.

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models · HackerPapers discussions

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models — mentioned by lmf4lol

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models — mentioned by teej