Evaluating Robustness of Generative Models with Adversarial Networks

Korn Sooksatra, Gissella Bejarano, Pablo Rivas

Keywords: Adversarial examples, Generative models, Generative adversarial networks, Adversarial attacks

Abstract: With the advent of adversarial robustness as a research area, much novel work attempts to design creative defense mechanisms against adversarial vulnerabilities that arise. While classification models are the most common target of adversarial robustness research, generative models are often underestimated though they play essential roles in many applications. This work evaluates generative models for reconstruction tasks in terms of their adversarial robustness. We constructed two frameworks: a standard and a universal-attack framework. The standard framework requires an input to find its perturbation, and the universal-attack framework generates adversarial perturbation from the distribution of a dataset. Extensive experimental evidence discussed in this paper suggests that both frameworks can effectively alter how images are reconstructed and classified using classic generative models trained on MNIST and Cropped Yale Face datasets. Further, these frameworks outperform state-of-the-art adversarial attacks. Moreover, we showcase using the proposed framework to retrain a generative model to improve its resilience against adversarial perturbations. Furthermore, for the sake of generative models, an attack may desire not to alter the latent space. Thus, we also include the analysis of the latent space.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning