Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks

Add code
Aug 21, 2024
Figure 1 for Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
Figure 2 for Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
Figure 3 for Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
Figure 4 for Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: