{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/pgd","entry":"pgd","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":18,"n_papers_ran":7,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":20,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":20,"n_places_pointer_only":12,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":0,"ran":3,"unverified":13},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2507.12843","paper":null,"title":"arXiv:2507.12843","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"zhijianzhouml/NAMMD","path":"ADV_exp/attack_generator.py","file_url":"https://github.com/zhijianzhouml/NAMMD/blob/HEAD/ADV_exp/attack_generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"28b14896c4e904e7","mcp_get_code":{"code_sha256":"28b14896c4e904e7"}},{"arxiv_id":"2506.03355","paper":"/paper/robustness-in-both-domains-clip-needs-a","title":"Robustness in Both Domains: CLIP Needs a Robust Text Encoder","date":"2025-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LIONS-EPFL/LEAF","path":"src/robust_vlm/train/adversarial_training_clip.py","file_url":"https://github.com/LIONS-EPFL/LEAF/blob/HEAD/src/robust_vlm/train/adversarial_training_clip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9a6cd97c45d4f91","mcp_get_code":{"code_sha256":"f9a6cd97c45d4f91"}},{"arxiv_id":"2406.18062","paper":"/paper/breaking-the-barrier-enhanced-utility-and","title":"Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5a2c00df265799e5","mcp_get_code":{"code_sha256":"5a2c00df265799e5"}},{"arxiv_id":"2404.08255","paper":"/paper/practical-region-level-attack-against-segment","title":"Practical Region-level Attack against Segment Anything Models","date":"2024-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShenYifanS/S-RA_T-RA","path":"SSAscripts/example.py","file_url":"https://github.com/ShenYifanS/S-RA_T-RA/blob/HEAD/SSAscripts/example.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"83995d3bc2efe6df","mcp_get_code":{"code_sha256":"83995d3bc2efe6df"}},{"arxiv_id":"2404.08255","paper":"/paper/practical-region-level-attack-against-segment","title":"Practical Region-level Attack against Segment Anything Models","date":"2024-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShenYifanS/S-RA_T-RA","path":"SSAscripts/example_multi.py","file_url":"https://github.com/ShenYifanS/S-RA_T-RA/blob/HEAD/SSAscripts/example_multi.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93ebcf9c9ccea222","mcp_get_code":{"code_sha256":"93ebcf9c9ccea222"}},{"arxiv_id":"2403.14398","paper":"/paper/regularized-adaptive-momentum-dual-averaging","title":"Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network","date":"2024-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ismoptgroup/ramda","path":"Core/optimizer.py","file_url":"https://github.com/ismoptgroup/ramda/blob/HEAD/Core/optimizer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a445e118c7ac9c43","mcp_get_code":{"code_sha256":"a445e118c7ac9c43"}},{"arxiv_id":"2403.04050","paper":"/paper/belief-enriched-pessimistic-q-learning","title":"Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations","date":"2024-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SliencerX/Belief-enriched-robust-Q-learning","path":"attacks.py","file_url":"https://github.com/SliencerX/Belief-enriched-robust-Q-learning/blob/HEAD/attacks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b04a1a19e73c0ebb","mcp_get_code":{"code_sha256":"b04a1a19e73c0ebb"}},{"arxiv_id":"2402.12336","paper":"/paper/robust-clip-unsupervised-adversarial-fine","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chs20/robustvlm","path":"train/adversarial_training_clip.py","file_url":"https://github.com/chs20/robustvlm/blob/HEAD/train/adversarial_training_clip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7062c33b2cc96026","mcp_get_code":{"code_sha256":"7062c33b2cc96026"}},{"arxiv_id":"2401.12532","paper":"/paper/dafa-distance-aware-fair-adversarial-training","title":"DAFA: Distance-Aware Fair Adversarial Training","date":"2024-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucy74/DAFA","path":"evaluation.py","file_url":"https://github.com/rucy74/DAFA/blob/HEAD/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1ca971f9ac6b177","mcp_get_code":{"code_sha256":"b1ca971f9ac6b177"}},{"arxiv_id":"2309.05145","paper":"/paper/outlier-robust-adversarial-training","title":"Outlier Robust Adversarial Training","date":"2023-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"discovershu/orat","path":"attack_generator.py","file_url":"https://github.com/discovershu/orat/blob/HEAD/attack_generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2ea2c513cf37e3ab","mcp_get_code":{"code_sha256":"2ea2c513cf37e3ab"}},{"arxiv_id":"2309.05145","paper":"/paper/outlier-robust-adversarial-training","title":"Outlier Robust Adversarial Training","date":"2023-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"discovershu/orat","path":"attack_generator_for_cifar100.py","file_url":"https://github.com/discovershu/orat/blob/HEAD/attack_generator_for_cifar100.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0dd83d1a63902700","mcp_get_code":{"code_sha256":"0dd83d1a63902700"}},{"arxiv_id":"2306.07197","paper":"/paper/aroid-improving-adversarial-robustness","title":"AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"treelli/aroid","path":"src/utils/adversary.py","file_url":"https://github.com/treelli/aroid/blob/HEAD/src/utils/adversary.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2fc76dc36847c6db","mcp_get_code":{"code_sha256":"2fc76dc36847c6db"}},{"arxiv_id":"2306.01435","paper":"/paper/improving-adversarial-robustness-of-deqs-with","title":"Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamics","date":"2023-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minicheshire/deq-regulating-neural-dynamics","path":"input-entropy-reduction/MDEQ-Vision/lib/core/cls_function.py","file_url":"https://github.com/minicheshire/deq-regulating-neural-dynamics/blob/HEAD/input-entropy-reduction/MDEQ-Vision/lib/core/cls_function.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"304e362a32930910","mcp_get_code":{"code_sha256":"304e362a32930910"}},{"arxiv_id":"2301.09879","paper":"/paper/data-augmentation-alone-can-improve","title":"Data Augmentation Alone Can Improve Adversarial Training","date":"2023-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"treelli/da-alone-improves-at","path":"src/utils/adversary.py","file_url":"https://github.com/treelli/da-alone-improves-at/blob/HEAD/src/utils/adversary.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e36d3bdff03face5","mcp_get_code":{"code_sha256":"e36d3bdff03face5"}},{"arxiv_id":"2210.05968","paper":"/paper/boosting-the-transferability-of-adversarial-2","title":"Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation","date":"2022-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alan-Qin/Transfer_attack_RAP","path":"rap_attack.py","file_url":"https://github.com/Alan-Qin/Transfer_attack_RAP/blob/HEAD/rap_attack.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"01c6e50ac9a6dc7e","mcp_get_code":{"code_sha256":"01c6e50ac9a6dc7e"}},{"arxiv_id":"2210.03543","paper":"/paper/a2-efficient-automated-attacker-for-boosting","title":"A2: Efficient Automated Attacker for Boosting Adversarial Training","date":"2022-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alipay/A2-efficient-automated-attacker-for-boosting-adversarial-training","path":"attack_generator.py","file_url":"https://github.com/alipay/A2-efficient-automated-attacker-for-boosting-adversarial-training/blob/HEAD/attack_generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cdf5b1330544a607","mcp_get_code":{"code_sha256":"cdf5b1330544a607"}},{"arxiv_id":"2003.01090","paper":"/paper/learn2perturb-an-end-to-end-feature","title":"Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness","date":"2020-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ahmadreza-Jeddi/Learn2Perturb","path":"attacks/pgd.py","file_url":"https://github.com/Ahmadreza-Jeddi/Learn2Perturb/blob/HEAD/attacks/pgd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e0919d109e7e3ae4","mcp_get_code":{"code_sha256":"e0919d109e7e3ae4"}},{"arxiv_id":"1906.03563","paper":"/paper/beyond-adversarial-training-min-max","title":"Adversarial Attack Generation Empowered by Min-Max Optimization","date":"2019-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangjksjtu/minmax-adv","path":"neurips21/attacks/pgd.py","file_url":"https://github.com/wangjksjtu/minmax-adv/blob/HEAD/neurips21/attacks/pgd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fed551f077ea431d","mcp_get_code":{"code_sha256":"fed551f077ea431d"}},{"arxiv_id":"1905.13736","paper":"/paper/unlabeled-data-improves-adversarial","title":"Unlabeled Data Improves Adversarial Robustness","date":"2019-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yguooo/semisup-adv","path":"attack_pgd.py","file_url":"https://github.com/yguooo/semisup-adv/blob/HEAD/attack_pgd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a23942fc2c20b6ab","mcp_get_code":{"code_sha256":"a23942fc2c20b6ab"}},{"arxiv_id":"1904.08489","paper":"/paper/semantic-adversarial-attacks-parametric","title":"Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers","date":"2019-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ameya005/Semantic_Adversarial_Attacks","path":"simple_classifier.py","file_url":"https://github.com/ameya005/Semantic_Adversarial_Attacks/blob/HEAD/simple_classifier.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2dc3218a6608cc0","mcp_get_code":{"code_sha256":"e2dc3218a6608cc0"}}]}