{"id":45142799,"url":"https://github.com/Harry24k/PGD-pytorch","last_synced_at":"2026-02-20T10:00:56.204Z","repository":{"id":42225221,"uuid":"181818297","full_name":"Harry24k/PGD-pytorch","owner":"Harry24k","description":"A pytorch implementation of \"Towards Deep Learning Models Resistant to Adversarial Attacks\"","archived":false,"fork":false,"pushed_at":"2019-09-04T14:46:07.000Z","size":636,"stargazers_count":156,"open_issues_count":1,"forks_count":38,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-09-07T15:43:14.666Z","etag":null,"topics":["adversarial-attacks","deep-learning","pytorch"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Harry24k.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-04-17T04:41:07.000Z","updated_at":"2025-07-04T16:02:55.000Z","dependencies_parsed_at":"2022-08-12T09:51:07.118Z","dependency_job_id":null,"html_url":"https://github.com/Harry24k/PGD-pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Harry24k/PGD-pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Harry24k%2FPGD-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Harry24k%2FPGD-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Harry24k%2FPGD-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Harry24k%2FPGD-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Harry24k","download_url":"https://codeload.github.com/Harry24k/PGD-pytorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Harry24k%2FPGD-pytorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29647768,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-20T09:27:29.698Z","status":"ssl_error","status_checked_at":"2026-02-20T09:26:12.373Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adversarial-attacks","deep-learning","pytorch"],"created_at":"2026-02-20T01:00:27.320Z","updated_at":"2026-02-20T10:00:56.177Z","avatar_url":"https://github.com/Harry24k.png","language":"Jupyter Notebook","funding_links":[],"categories":["🛡️ Adversarial Testing","Jupyter Notebook"],"sub_categories":[],"readme":"# PGD-pytorch\n**A pytorch implementation of \"[Towards Deep Learning Models Resistant to Adversarial Attacks](https://arxiv.org/abs/1706.06083)\"**\n\n## Summary\nThis code is a pytorch implementation of **PGD attack**   \nIn this code, I used above methods to fool [Inception v3](https://arxiv.org/abs/1512.00567).   \n'[Giant Panda](http://www.image-net.org/)' used for an example.   \nYou can add other pictures with a folder with the label name in the 'data/imagenet'.    \n\n## Requirements\n* python==3.6   \n* numpy==1.14.2   \n* pytorch==1.0.1   \n\n## Important results not in the code\n- Capacity(size of network) plays an important role in adversarial training. (p.9-10)\n\t- For only natural examples training, it increases the robustness against one-step perturbations.\n\t- For PGD adversarial training, small capacity networks fails.\n\t- As capacity increases, the model can fit the adversairal examples increasingly well.\n\t- More capacity and strong adversaries decrease transferability. (Section B)\n- FGSM adversaries don't increase robustness for large epsilon(=8). (p.9-10)\n\t- The network overfit to FGSM adversarial examples.\n- Adversarial training with PGD shows good enough defense results.(p.12-13)\n\n## Notice\n- This Repository won't be updated.\n- Please check [the package of adversarial attacks in pytorch](https://github.com/Harry24k/adversairal-attacks-pytorch)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHarry24k%2FPGD-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FHarry24k%2FPGD-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHarry24k%2FPGD-pytorch/lists"}