English
Related papers

Related papers: On the tightness of linear relaxation based robust…

200 papers

White box adversarial perturbations are sought via iterative optimization algorithms most often minimizing an adversarial loss on a $l_p$ neighborhood of the original image, the so-called distortion set. Constraining the adversarial search…

Machine Learning · Computer Science 2020-07-06 Ehsan Kazemi , Thomas Kerdreux , Liqiang Wang

Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propose a new algorithm,…

Machine Learning · Computer Science 2020-02-19 Minhao Cheng , Qi Lei , Pin-Yu Chen , Inderjit Dhillon , Cho-Jui Hsieh

The robustness of deep neural networks has received significant interest recently, especially when being deployed in safety-critical systems, as it is important to analyze how sensitive the model output is under input perturbations. While…

Machine Learning · Computer Science 2022-03-29 Zhilu Wang , Chao Huang , Qi Zhu

We improve the effectiveness of propagation- and linear-optimization-based neural network verification algorithms with a new tightened convex relaxation for ReLU neurons. Unlike previous single-neuron relaxations which focus only on the…

Machine Learning · Computer Science 2020-10-26 Christian Tjandraatmadja , Ross Anderson , Joey Huchette , Will Ma , Krunal Patel , Juan Pablo Vielma

Recent studies have highlighted the potential of Lipschitz-based methods for training certifiably robust neural networks against adversarial attacks. A key challenge, supported both theoretically and empirically, is that robustness demands…

Machine Learning · Computer Science 2024-06-25 Kai Hu , Klas Leino , Zifan Wang , Matt Fredrikson

Randomized smoothing, a method to certify a classifier's decision on an input is invariant under adversarial noise, offers attractive advantages over other certification methods. It operates in a black-box and so certification is not…

Machine Learning · Computer Science 2020-06-09 Jamie Hayes

Adversarial training can considerably robustify deep neural networks to resist adversarial attacks. However, some works suggested that adversarial training might comprise the privacy-preserving and generalization abilities. This paper…

Machine Learning · Computer Science 2020-12-29 Fengxiang He , Shaopeng Fu , Bohan Wang , Dacheng Tao

Since neural classifiers are known to be sensitive to adversarial perturbations that alter their accuracy, \textit{certification methods} have been developed to provide provable guarantees on the insensitivity of their predictions to such…

Machine Learning · Computer Science 2025-02-26 Cornelius Emde , Francesco Pinto , Thomas Lukasiewicz , Philip H. S. Torr , Adel Bibi

Neural Lyapunov and barrier certificates have recently been used as powerful tools for verifying the safety and stability properties of deep reinforcement learning (RL) controllers. However, existing methods offer guarantees only under…

Machine Learning · Computer Science 2026-02-06 Chengxiao Wang , Haoze Wu , Gagandeep Singh

Neural network certification methods heavily rely on convex relaxations to provide robustness guarantees. However, these relaxations are often imprecise: even the most accurate single-neuron relaxation is incomplete for general ReLU…

Machine Learning · Computer Science 2026-02-23 Yuhao Mao , Yani Zhang , Martin Vechev

Over the years, researchers have developed myriad attacks that exploit the ubiquity of adversarial examples, as well as defenses that aim to guard against the security vulnerabilities posed by such attacks. Of particular interest to this…

Machine Learning · Computer Science 2023-10-17 Ravi Mangal , Klas Leino , Zifan Wang , Kai Hu , Weicheng Yu , Corina Pasareanu , Anupam Datta , Matt Fredrikson

Distributionally Robust (DR) optimization aims to certify worst-case risk within a Wasserstein uncertainty set. Current certifications typically rely either on global Lipschitz bounds, which are often conservative, or on local gradient…

Optimization and Control · Mathematics 2026-04-09 Hong T. M. Chu

Verifying robustness of neural network classifiers has attracted great interests and attention due to the success of deep neural networks and their unexpected vulnerability to adversarial perturbations. Although finding minimum adversarial…

Machine Learning · Statistics 2018-11-30 Akhilan Boopathy , Tsui-Wei Weng , Pin-Yu Chen , Sijia Liu , Luca Daniel

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Machine Learning · Computer Science 2024-03-15 Daiwei Yu , Zhuorong Li , Lina Wei , Canghong Jin , Yun Zhang , Sixian Chan

As reinforcement learning (RL) has achieved great success and been even adopted in safety-critical domains such as autonomous vehicles, a range of empirical studies have been conducted to improve its robustness against adversarial attacks.…

Machine Learning · Computer Science 2022-03-17 Fan Wu , Linyi Li , Zijian Huang , Yevgeniy Vorobeychik , Ding Zhao , Bo Li

Generative neural networks can be used to specify continuous transformations between images via latent-space interpolation. However, certifying that all images captured by the resulting path in the image manifold satisfy a given property…

Machine Learning · Computer Science 2020-05-01 Matthew Mirman , Timon Gehr , Martin Vechev

Post-hoc explanation methods are used with the intent of providing insights about neural networks and are sometimes said to help engender trust in their outputs. However, popular explanations methods have been found to be fragile to minor…

Machine Learning · Computer Science 2022-12-19 Matthew Wicker , Juyeon Heo , Luca Costabello , Adrian Weller

Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently. However, current robustness certification methods are only able to certify under a limited perturbation…

Machine Learning · Computer Science 2023-04-13 Zhuolin Yang , Zhikuan Zhao , Boxin Wang , Jiawei Zhang , Linyi Li , Hengzhi Pei , Bojan Karlas , Ji Liu , Heng Guo , Ce Zhang , Bo Li

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…

Machine Learning · Statistics 2023-06-02 Dongyoon Yang , Insung Kong , Yongdai Kim

Recent studies have shown that modern deep neural network classifiers are easy to fool, assuming that an adversary is able to slightly modify their inputs. Many papers have proposed adversarial attacks, defenses and methods to measure…

Machine Learning · Computer Science 2020-03-17 Igor Buzhinsky , Arseny Nerinovsky , Stavros Tripakis