Search Results for author:
Found 13 papers, 6 papers with code
Rapid Development of Compositional AI
Compositional AI systems, which combine multiple artificial intelligence components together with other application components to solve a larger problem, have no known pattern of development and are often approached in a bespoke and ad hoc style.
Distributed Adversarial Training to Robustify Deep Neural Networks at Scale
Spurred by that, we propose distributed adversarial training (DAT), a large-batch adversarial training framework implemented over multiple machines.
When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
We show that AdvCL is able to enhance cross-task robustness transferability without loss of model accuracy and finetuning efficiency.
Generating Realistic Physical Adversarial Examplesby Patch Transformer Network
Physical adversarial attacks apply carefully crafted adversarial perturbations onto real objects to maliciously alter the prediction of object classifiers or detectors.
Generating Adversarial Computer Programs using Optimized Obfuscations
We further show that our formulation is better at training models that are robust to adversarial attacks.
Fast Training of Provably Robust Neural Networks by SingleProp
Recent works have developed several methods of defending neural networks against adversarial attacks with certified guarantees.
Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
When the training data are maliciously tampered, the predictions of the acquired deep neural network (DNN) can be manipulated by an adversary known as the Trojan attack (or poisoning backdoor attack).
Proper Network Interpretability Helps Adversarial Robustness in Classification
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to adversarial attacks.
A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning
Zeroth-order (ZO) optimization is a subset of gradient-free optimization that emerges in many signal processing and machine learning applications.
Adversarial T-shirt! Evading Person Detectors in A Physical World
To the best of our knowledge, this is the first work that models the effect of deformation for designing physical adversarial examples with respect to-rigid objects such as T-shirts.
Reflecting After Learning for Understanding
Using the framework on images from ImageNet, we demonstrate systems that unify 41% to 46% of predictions in general and unify 67% to 75% of predictions when the systems can explain their conceptual differences.
Visual Interpretability Alone Helps Adversarial Robustness
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability, and interpretability is itself susceptible to adversarial attacks.
Interpreting Adversarial Examples by Activation Promotion and Suppression
It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers.
