Tianyu Pang, Min Lin, Shuicheng Yan, Chao Du, Zekai Wang, Weiwei Liu
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.
It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusion models, a question naturally arises: can better diffusion models further improve adversarial training? This paper gives an affirmative answer by employing the most recent diffusion model (Karras et al., 2022) which has higher efficiency (∼ 20 sampling steps) and image quality (lower FID score) compared with DDPM. Our adversarially trained models achieve state-of-the-art performance on RobustBench using only generated data (no external datasets). Under the ℓ ∞norm threat model with ϵ = 8/255, our models achieve 70.69% and 42.67% robust accuracy on CIFAR-10 and CIFAR-100, respectively, i.e. improving upon previous state-of-the-art models by +4.58% and +8.03%. Under the ℓ 2 -norm threat model with ϵ = 128/255, our models achieve 84.86% on CIFAR-10 (+4.44%). These results also beat previous works that use external data. We also provide compelling results on the SVHN and TinyImageNet datasets. Our code is at https://github.com/wzekai99/DM-Improves-AT.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.04638")
get_code_for_paper("2302.04638")
have("2302.04638")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2302.04638.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2302.04638)
Connect an agent — have() is free.