{"id":20266656,"url":"https://github.com/gurbaaz27/cs776a-course-project","last_synced_at":"2025-04-11T03:22:33.559Z","repository":{"id":67115364,"uuid":"480431812","full_name":"gurbaaz27/CS776A-Course-Project","owner":"gurbaaz27","description":"Can Adversarial training defend against Poisoning attacks?","archived":false,"fork":false,"pushed_at":"2022-07-28T13:21:20.000Z","size":46904,"stargazers_count":4,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-25T01:11:41.857Z","etag":null,"topics":["adversarial-attacks","adversarial-training","backdoor-attacks","cnn-keras","computer-vision","deep-learning","poisoning-attack"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gurbaaz27.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-04-11T15:07:51.000Z","updated_at":"2024-08-06T09:24:10.000Z","dependencies_parsed_at":"2023-06-09T18:45:19.909Z","dependency_job_id":null,"html_url":"https://github.com/gurbaaz27/CS776A-Course-Project","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gurbaaz27%2FCS776A-Course-Project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gurbaaz27%2FCS776A-Course-Project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gurbaaz27%2FCS776A-Course-Project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gurbaaz27%2FCS776A-Course-Project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gurbaaz27","download_url":"https://codeload.github.com/gurbaaz27/CS776A-Course-Project/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248334331,"owners_count":21086375,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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","adversarial-training","backdoor-attacks","cnn-keras","computer-vision","deep-learning","poisoning-attack"],"created_at":"2024-11-14T12:10:44.437Z","updated_at":"2025-04-11T03:22:33.550Z","avatar_url":"https://github.com/gurbaaz27.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CS776A: Deep Learning for Computer Vision \n## Course Project: Adversarial Training Is All You Need\n\n### Table of Contents\n\n1. [Code](#code)\n2. [Implementation References](#implementation-references)\n3. [Presentations](#presentations)\n4. [Team Details](#team-details)\n\n## Code \n\n- Abstract is present as `CS776_Project_Abstract_grp1.pdf`\n- Final Report is present as `CS776_Project_Report_grp1.pdf`\n- Presentations are present in `presentations/` directory.\n- Colab notebooks are present in offline form in `noteboooks/` directory. You may upload them on `colab` to run, or simply install all the dependencies to run locally.\n- Trained weights are present in `weights/` directory. \n- The attacks and trainers have been implemented and are present in `src/` directory.\n- Sample tests showing how to import and run code from `src/` are present in `test/` directory.\n- To install the dependencies present in `requirements.txt`, run the following code\n\n```\npython -m venv venv\nsource venv/bin/activate\npip install -r requirements.txt\n```\n\n## Implementation References\n\n![](/assets/model.png)\n\n1. Projected Gradient Descent : \u003chttps://arxiv.org/abs/1706.06083\u003e\n2. Fast Gradient : \u003chttps://arxiv.org/abs/1412.6572\u003e\n3. Poisoning Backdoor Attack : \u003chttps://arxiv.org/abs/1708.06733\u003e\n4. Clean Label Backdoor Attack : \u003chttps://people.csail.mit.edu/madry/lab/cleanlabel.pdf\u003e \n5. Adversarial Trainer: \u003chttps://arxiv.org/abs/1705.07204\u003e\n\n\u003c!-- ## Colab Notebooks\n\n- \u003chttps://colab.research.google.com/drive/1st-2urEYh3zUzRjQHLk8mF21CRW-j48j\u003e\n- \u003chttps://colab.research.google.com/drive/1LsGm57CCM59XZsBnDemfA8BAb9bsFvc5\u003e\n- \u003chttps://colab.research.google.com/drive/1ASzUn1f-UtFs7r2gLzYyPMqpziidrtvr\u003e\n- \u003chttps://colab.research.google.com/drive/1yfazdiEITrw6fqIqmLMOjCOpJzung6bl\u003e\n- \u003chttps://colab.research.google.com/drive/1j1pNCxpCVsQVQqS0UzJyOjHdOZ6payOy\u003e\n- \u003chttps://colab.research.google.com/drive/1zYajEB6NWIynRoAtzXy6HT68Lf0M304M\u003e\n- \u003chttps://colab.research.google.com/drive/1C0GY6tWKJEuI2n01J3o0XobuD-3qCxgb\u003e\n- \u003chttps://colab.research.google.com/drive/1BgFlnf_j7YI2tSP9POMOSObPAVZDUWti\u003e\n- \u003chttps://colab.research.google.com/drive/1vRpH6CSp_R9dSX_lYIlkTGpy9fka2vMG\u003e\n- \u003chttps://colab.research.google.com/drive/1AGdIa8MX16Tq14KY2NTep8XyOGMA5c0b\u003e --\u003e\n\n## Presentations\n\n- [Introduction](https://docs.google.com/presentation/d/1MmP0-k36qOBBNjjmTbijOYmaXke5C320Nk0bbWvtvHs/edit?usp=sharing)\n- [MidTerm](https://docs.google.com/presentation/d/1nM_yWx62foza3gbXtWaH5z8jiSWkhmBDAvXaYklACuI/edit?usp=sharing)\n- [EndTerm](https://docs.google.com/presentation/d/15msRML-j4l8fJDiF01JdxQi4W_CI6NPOQ-SlDda5v48/edit?usp=sharing)\n\n## Team Details\n\n- Name : Four of a Kind\n\n- Members :\n\n| **Name** | **Roll No.** | \n| ----------- | ----------- |\n| Antreev Singh Brar | 190163 | \n| Anubhav Kalyani | 190164 |\n| Gurbaaz Singh Nandra | 190349 |\n| Pramodh V Gopalan | 190933 |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgurbaaz27%2Fcs776a-course-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgurbaaz27%2Fcs776a-course-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgurbaaz27%2Fcs776a-course-project/lists"}