We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We develop a novel optimization method for NLPbackdoor inversion. We leverage a dynamically reducing temperature coefficient in the softmax function to provide changing loss landscapes to the optimizer such that the process gradually focuses on the ground truth trigger, which is denoted as a one-hot value in a convex hull. Our method also features a temperature rollback mechanism to step away from local optimals, exploiting the observation that local optimals can be easily deter-mined in NLP trigger inversion (while not in general optimization). We evaluate the technique on over 1600 models (with roughly half of them having injected backdoors) on 3 prevailing NLP tasks, with 4 different backdoor attacks and 7 architectures. Our results show that the technique is able to effectively and efficiently detect and remove backdoors, outperforming 4 baseline methods.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2202.05749")
get_code_for_paper("2202.05749")
have("2202.05749")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2202.05749.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2202.05749)
Connect an agent — have() is free.