{"id":4655,"date":"2025-06-17T07:02:33","date_gmt":"2025-06-17T07:02:33","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/06\/17\/2506-12454\/"},"modified":"2025-06-17T07:02:33","modified_gmt":"2025-06-17T07:02:33","slug":"2506-12454","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/06\/17\/2506-12454\/","title":{"rendered":"On the existence of consistent adversarial attacks in high-dimensional linear classification"},"content":{"rendered":"

On the existence of consistent adversarial attacks in high-dimensional linear classification
\n \t

\n
<\/BR>
\n
\n \t

\n
<\/BR><\/p>\n

arXiv:2506.12454v1 Announce Type: new
\nAbstract: What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this work, we investigate this question in the setting of high-dimensional binary classification, where statistical effects due to limited data availability play a central role. We introduce a new error metric that precisely capture this distinction, quantifying model vulnerability to consistent adversarial attacks — perturbations that preserve the ground-truth labels. Our main technical contribution is an exact and rigorous asymptotic characterization of these metrics in both well-specified models and latent space models, revealing different vulnerability patterns compared to standard robust error measures. The theoretical results demonstrate that as models become more overparameterized, their vulnerability to label-preserving perturbations grows, offering theoretical insight into the mechanisms underlying model sensitivity to adversarial attacks.<\/div>\n

\t

\n
<\/BR>
\n Matteo Vilucchio, Lenka Zdeborov’a, Bruno Loureiro
\n \t

\n
<\/BR>
\nGo to original source<\/a>
\n \t

\n
<\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"

On the existence of consistent adversarial attacks in high-dimensional linear classification arXiv:2506.12454v1 Announce Type: new Abstract: What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this work, we investigate this question in the setting of high-dimensional binary classification, where statistical effects due to limited data availability […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,1878,412,113,112],"tags":[1382,1921,236],"class_list":["post-4655","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cond-mat-dis-nn","category-cs-cr","category-cs-lg","category-stat-ml","tag-adversarial","tag-attacks","tag-consistent"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/4655"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=4655"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/4655\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=4655"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=4655"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=4655"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}