adversarial loss
On The Existence of The Adversarial Bayes Classifier
While it has been the subject of several recent theoretical studies, many important questions related to adversarial robustness are still open.
Calibration and Consistency of Adversarial Surrogate Losses
Adversarial robustness is an increasingly critical property of classifiers in applications. The design of robust algorithms relies on surrogate losses since the optimization of the adversarial loss with most hypothesis sets is NP-hard. But, which surrogate losses should be used and when do they benefit from theoretical guarantees? We present an extensive study of this question, including a detailed analysis of the H-calibration and H-consistency of adversarial surrogate losses. We show that convex loss functions, or the supremum-based convex losses often used in applications, are not H-calibrated for common hypothesis sets used in machine learning.
Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3DShape Synthesis
We introduce DMTET, a deep 3D conditional generative model that can synthesize high-resolution 3D shapes using simple user guides such as coarse voxels.
KDGAN: Knowledge Distillation with Generative Adversarial Networks
Knowledge distillation (KD) aims to train a lightweight classifier suitable to provide accurate inference with constrained resources in multi-label learning. Instead of directly consuming feature-label pairs, the classifier is trained by a teacher, i.e., a high-capacity model whose training may be resource-hungry. The accuracy of the classifier trained this way is usually suboptimal because it is difficult to learn the true data distribution from the teacher. An alternative method is to adversarially train the classifier against a discriminator in a two-player game akin to generative adversarial networks (GAN), which can ensure the classifier to learn the true data distribution at the equilibrium of this game. However, it may take excessively long time for such a two-player game to reach equilibrium due to high-variance gradient updates.
Content preserving text generation with attribute controls
Lajanugen Logeswaran, Honglak Lee, Samy Bengio
We focus on categorical attributes of language. Examples of such attributes include sentiment, language complexity, tense, voice, honorifics, mood, etc. Our approach draws inspiration from styletransfer methods inthevision andlanguage literature.
Adversarial Training from Mean Field Perspective
We also show that the network width alleviates these issues.
Improved Generation of Adversarial Examples Against Safety-aligned LLMs Qizhang Li
Yiwen Guo leads the project and serves as the corresponding author.