Jailbreak in LLM Malicious Use - Backdoor Attack

"However, there are still ones who can leave holes in the training dataset, making LLMs appear safe on average, but generate harmful content under other specific conditions. This kind of attack can be categorized as "backdoor attack". Evan et al. developed a backdoor model that behaves as expected when trained, but exhibits different and potentially harmful behavior when deployed [81]. The results show that these backdoor behaviors persist even after multiple security training techniques are applied."(p. 21)