Search Results for author:
Found 21 papers, 7 papers with code
Compressing GANs using Knowledge Distillation
From our experiments, we observe a qualitative limit for GAN's compression.
Improved Training of Certifiably Robust Models
Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical (PGD) robustness.
WITCHcraft: Efficient PGD attacks with random step size
State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points.
Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers
Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical robustness.
Certified Defenses for Adversarial Patches
Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems.
Certifying Strategyproof Auction Networks
We focus on the RegretNet architecture, which can represent auctions with arbitrary numbers of items and participants; it is trained to be empirically strategyproof, but the property is never exactly verified leaving potential loopholes for market participants to exploit.
Detection as Regression: Certified Object Detection by Median Smoothing
While adversarial training can improve the empirical robustness of image classifiers, a direct extension to object detection is very expensive.
WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic
Low-resolution neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity.
ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learning
Inspired by these advances, in this paper, we extend techniques for approximating auctions using deep learning to address concerns of fairness while maintaining high revenue and strong incentive guarantees.
Detection as Regression: Certified Object Detection with Median Smoothing
Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date.
Certified Watermarks for Neural Networks
Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio.
WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic
Low-precision neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity.
Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release
Large organizations such as social media companies continually release data, for example user images.
Adversarial Examples Make Strong Poisons
The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data.
Protecting Proprietary Data: Poisoning for Secure Dataset Release
These two behaviors can be in conflict as an organization wants to prevent competitors from using their own data to replicate the performance of their proprietary models.
Active Learning at the ImageNet Scale
Active learning (AL) algorithms aim to identify an optimal subset of data for annotation, such that deep neural networks (DNN) can achieve better performance when trained on this labeled subset.
Certified Neural Network Watermarks with Randomized Smoothing
Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio.
K-SAM: Sharpness-Aware Minimization at the Speed of SGD
Sharpness-Aware Minimization (SAM) has recently emerged as a robust technique for improving the accuracy of deep neural networks.
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
We find that the weakness of existing discrete optimizers for text, combined with the relatively high costs of optimization, makes standard adaptive attacks more challenging for LLMs.
NEFTune: Noisy Embeddings Improve Instruction Finetuning
We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation.
Universal Pyramid Adversarial Training for Improved ViT Performance
Recently, Pyramid Adversarial training (Herrmann et al., 2022) has been shown to be very effective for improving clean accuracy and distribution-shift robustness of vision transformers.
