activity
20192024
most citedOn Physical Adversarial Patches for Object Detection

115 citations · 188 across the 12 of their papers we have counts for

collaborators

6 papers

cs.CL2021

Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits

Leonid Boytsov, Zico Kolter

We study the utility of the lexical translation model (IBM Model 1) for English text retrieval, in particular, its neural variants that are trained end-to-end. We use the neural Mo…

cs.LG2021

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification

Shiqi Wang, Huan Zhang, Kaidi Xu +4

Bound propagation based incomplete neural network verifiers such as CROWN are very efficient and can significantly accelerate branch-and-bound (BaB) based complete verification of…

cs.LG20213 cited

You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries

Devin Willmott, Anit Kumar Sahu, Fatemeh Sheikholeslami +2

Researchers have repeatedly shown that it is possible to craft adversarial attacks on deep classifiers (small perturbations that significantly change the class label), even in the…

cs.LG20201 cited

Provably robust deep generative models

Filipe Condessa, Zico Kolter

Recent work in adversarial attacks has developed provably robust methods for training deep neural network classifiers. However, although they are often mentioned in the context of…

cs.CV2019115 cited

On Physical Adversarial Patches for Object Detection

Mark Lee, Zico Kolter

In this paper, we demonstrate a physical adversarial patch attack against object detectors, notably the YOLOv3 detector. Unlike previous work on physical object detection attacks,…

cs.LG201943 cited

SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver

Po-Wei Wang, Priya L. Donti, Bryan Wilder +1

Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introduci…