Search Results for author:
Found 9 papers, 5 papers with code
Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think
We also find that PDMs can be used as an off-the-shelf purifier to effectively remove the adversarial patterns that were generated on LDMs to protect the images, which means that most protection methods nowadays, to some extent, cannot protect our images from malicious attacks.
Toward effective protection against diffusion based mimicry through score distillation
In this work, we present novel findings on attacking latent diffusion models (LDM) and propose new plug-and-play strategies for more effective protection.
Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models.
Syntax-guided Localized Self-attention by Constituency Syntactic Distance
Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data.
Bil-DOS: A Bi-lingual Dialogue Ordering System (for Subway)
Due to the unfamiliarity to particular words(or proper nouns) for ingredients, non-native English speakers can be extremely confused about the ordering process in restaurants like Subway.
CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
In this paper, we investigate GNNs from the lens of weight and feature loss landscapes, i. e., the loss changes with respect to model weights and node features, respectively.
A HYPOTHESIS FOR THE COGNITIVE DIFFICULTY OF IMAGES
This paper proposes a hypothesis to analyze the underlying reason for the cognitive difficulty of an image from two perspectives, i. e. a cognitive image usually makes a DNN strongly activated by cognitive concepts; discarding massive non-cognitive concepts may also help the DNN focus on cognitive concepts.
A Hypothesis for the Aesthetic Appreciation in Neural Networks
This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts.
Towards a Unified Evaluation of Explanation Methods without Ground Truth
This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges.
