{"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":"/paper/adversarial-robustness-of-b-vae-through-the","title":"Adversarial robustness of VAEs through the lens of local geometry","arxiv_id":"2208.03923","date":"2022-08-08","proceeding":null,"authors":["Asif Khan","Amos Storkey"],"abstract":"In an unsupervised attack on variational autoencoders (VAEs), an adversary finds a small perturbation in an input sample that significantly changes its latent space encoding, thereby compromising the reconstruction for a fixed decoder. A known reason for such vulnerability is the distortions in the latent space resulting from a mismatch between approximated latent posterior and a prior distribution. Consequently, a slight change in an input sample can move its encoding to a low/zero density region in the latent space resulting in an unconstrained generation. This paper demonstrates that an optimal way for an adversary to attack VAEs is to exploit a directional bias of a stochastic pullback metric tensor induced by the encoder and decoder networks. The pullback metric tensor of an encoder measures the change in infinitesimal latent volume from an input to a latent space. Thus, it can be viewed as a lens to analyse the effect of input perturbations leading to latent space distortions. We propose robustness evaluation scores using the eigenspectrum of a pullback metric tensor. Moreover, we empirically show that the scores correlate with the robustness parameter $\\beta$ of the $\\beta-$VAE. Since increasing $\\beta$ also degrades reconstruction quality, we demonstrate a simple alternative using \\textit{mixup} training to fill the empty regions in the latent space, thus improving robustness with improved reconstruction.","url_abs":"https://arxiv.org/abs/2208.03923v3","url_pdf":"https://arxiv.org/pdf/2208.03923v3.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":"adversarial-robustness-of-b-vae-through-the","repo_url":"https://github.com/mdasifkhan/robustnessvae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2208.03923","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}