{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/bridging-adversarial-robustness-and-gradient","title":"Bridging Adversarial Robustness and Gradient Interpretability","arxiv_id":"1903.11626","date":"2019-03-27","proceeding":null,"authors":["Beomsu Kim","Junghoon Seo","Taegyun Jeon"],"abstract":"Adversarial training is a training scheme designed to counter adversarial\nattacks by augmenting the training dataset with adversarial examples.\nSurprisingly, several studies have observed that loss gradients from\nadversarially trained DNNs are visually more interpretable than those from\nstandard DNNs. Although this phenomenon is interesting, there are only few\nworks that have offered an explanation. In this paper, we attempted to bridge\nthis gap between adversarial robustness and gradient interpretability. To this\nend, we identified that loss gradients from adversarially trained DNNs align\nbetter with human perception because adversarial training restricts gradients\ncloser to the image manifold. We then demonstrated that adversarial training\ncauses loss gradients to be quantitatively meaningful. Finally, we showed that\nunder the adversarial training framework, there exists an empirical trade-off\nbetween test accuracy and loss gradient interpretability and proposed two\npotential approaches to resolving this trade-off.","url_abs":"http://arxiv.org/abs/1903.11626v2","url_pdf":"http://arxiv.org/pdf/1903.11626v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bridging-adversarial-robustness-and-gradient","repo_url":"https://github.com/1202kbs/Robustness-and-Interpretability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.11626","atlas_url":"https://app.syntology.ai/?focus=1903.11626","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1903.11626"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1903.11626\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1903.11626"},"call":"get_concepts_for_paper(arxiv_id=\"1903.11626\")"}],"by_repo":[{"repo":"1202kbs/Robustness-and-Interpretability","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"8a59f97abadf033dd798a94b9d60a194870e8c00405c55449d5fb7b133cf09e4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}