1.8k citations · 3.9k across the 26 of their papers we have counts for
14 papers · 1 filter
DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing
Jiawei Zhang, Zhongzhu Chen, Huan Zhang +2
Diffusion models have been leveraged to perform adversarial purification and thus provide both empirical and certified robustness for a standard model. On the other hand, different…
Provably Bounding Neural Network Preimages
Suhas Kotha, Christopher Brix, Zico Kolter +2
Most work on the formal verification of neural networks has focused on bounding the set of outputs that correspond to a given set of inputs (for example, bounded perturbations of a…
Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness
Tianlong Chen, Huan Zhang, Zhenyu Zhang +4
Certifiable robustness is a highly desirable property for adopting deep neural networks (DNNs) in safety-critical scenarios, but often demands tedious computations to establish. Th…
Robustness Verification for Transformers
Zhouxing Shi, Huan Zhang, Kai-Wei Chang +2
Robustness verification that aims to formally certify the prediction behavior of neural networks has become an important tool for understanding model behavior and obtaining safety…
Towards Stable and Efficient Training of Verifiably Robust Neural Networks
Huan Zhang, Hongge Chen, Chaowei Xiao +5
Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under pertur…
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
Hadi Salman, Greg Yang, Jerry Li +4
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to -norm ad…
Robustness Verification of Tree-based Models
Hongge Chen, Huan Zhang, Si Si +3
We study the robustness verification problem for tree-based models, including decision trees, random forests (RFs) and gradient boosted decision trees (GBDTs). Formal robustness ve…
Robust Decision Trees Against Adversarial Examples
Hongge Chen, Huan Zhang, Duane Boning +1
Although adversarial examples and model robustness have been extensively studied in the context of linear models and neural networks, research on this issue in tree-based models an…
A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks
Hadi Salman, Greg Yang, Huan Zhang +2
Verification of neural networks enables us to gauge their robustness against adversarial attacks. Verification algorithms fall into two categories: exact verifiers that run in expo…
Efficient Neural Network Robustness Certification with General Activation Functions
Huan Zhang, Tsui-Wei Weng, Pin-Yu Chen +2
Finding minimum distortion of adversarial examples and thus certifying robustness in neural network classifiers for given data points is known to be a challenging problem. Neverthe…
Structured Adversarial Attack: Towards General Implementation and Better Interpretability
Kaidi Xu, Sijia Liu, Pu Zhao +6
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and a…
Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach
Minhao Cheng, Thong Le, Pin-Yu Chen +3
We study the problem of attacking a machine learning model in the hard-label black-box setting, where no model information is revealed except that the attacker can make queries to…
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
Minhao Cheng, Jinfeng Yi, Pin-Yu Chen +2
Crafting adversarial examples has become an important technique to evaluate the robustness of deep neural networks (DNNs). However, most existing works focus on attacking the image…
Towards Robust Neural Networks via Random Self-ensemble
Xuanqing Liu, Minhao Cheng, Huan Zhang +1
Recent studies have revealed the vulnerability of deep neural networks: A small adversarial perturbation that is imperceptible to human can easily make a well-trained deep neural n…