Turnitin
降AI改写
早检测系统
早降重系统
Turnitin-UK版
万方检测-期刊版
维普编辑部版
Grammarly检测
Paperpass检测
checkpass检测
PaperYY检测
Connecting certified and adversarial training
Training certifiably robust neural networks remains a notoriously hard problem. While
adversarial training optimizes under-approximations of the worst-case loss, which leads to …
adversarial training optimizes under-approximations of the worst-case loss, which leads to …
Ctbench: A library and benchmark for certified training
Training certifiably robust neural networks is an important but challenging task. While many
algorithms for (deterministic) certified training have been proposed, they are often evaluated …
algorithms for (deterministic) certified training have been proposed, they are often evaluated …
Expressive losses for verified robustness via convex combinations
In order to train networks for verified adversarial robustness, it is common to over-
approximate the worst-case loss over perturbation regions, resulting in networks that attain …
approximate the worst-case loss over perturbation regions, resulting in networks that attain …
Expressivity of reLU-networks under convex relaxations
Convex relaxations are a key component of training and certifying provably safe neural
networks. However, despite substantial progress, a wide and poorly understood accuracy …
networks. However, despite substantial progress, a wide and poorly understood accuracy …
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
Generalization of machine learning models can be severely compromised by data
poisoning, where adversarial changes are applied to the training data. This vulnerability has …
poisoning, where adversarial changes are applied to the training data. This vulnerability has …
Improve certified training with signal-to-noise ratio loss to decrease neuron variance and increase neuron stability
Neural network robustness is a major concern in safety-critical applications. Certified
robustness provides a reliable lower bound on worst-case robustness, and certified training …
robustness provides a reliable lower bound on worst-case robustness, and certified training …
Defending against Adversarial Malware Attacks on ML-based Android Malware Detection Systems
Android malware presents a persistent threat to users' privacy and data integrity. To combat
this, researchers have proposed machine learning-based (ML-based) Android malware …
this, researchers have proposed machine learning-based (ML-based) Android malware …
Multi-Neuron Unleashes Expressivity of ReLU Networks Under Convex Relaxation
Neural work certification has established itself as a crucial tool for ensuring the robustness of
neural networks. Certification methods typically rely on convex relaxations of the feasible …
neural networks. Certification methods typically rely on convex relaxations of the feasible …
Average Certified Radius is a Poor Metric for Randomized Smoothing
Randomized smoothing is a popular approach for providing certified robustness guarantees
against adversarial attacks, and has become a very active area of research. Over the past …
against adversarial attacks, and has become a very active area of research. Over the past …
Make Interval Bound Propagation great again
In various scenarios motivated by real life, such as medical data analysis, autonomous
driving, and adversarial training, we are interested in robust deep networks. A network is …
driving, and adversarial training, we are interested in robust deep networks. A network is …