English
Related papers

Related papers: Breaking the Adversarial Robustness-Performance Tr…

200 papers

Adversarially perturbed images of text can cause sophisticated OCR systems to produce misleading or incorrect transcriptions from seemingly invisible changes to humans. Some of these perturbations even survive physical capture, posing…

Machine Learning · Computer Science 2025-11-21 Bhagyesh Kumar , A S Aravinthakashan , Akshat Satyanarayan , Ishaan Gakhar , Ujjwal Verma

Deep learning classifiers are susceptible to well-crafted, imperceptible variations of their inputs, known as adversarial attacks. In this regard, the study of powerful attack models sheds light on the sources of vulnerability in these…

Machine Learning · Computer Science 2020-10-26 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

Fairness in machine learning is increasingly critical, yet standard approaches often treat data as static points in a high-dimensional space, ignoring the underlying generative structure. We posit that sensitive attributes (e.g., race,…

Machine Learning · Computer Science 2026-01-07 Vidhi Rathore

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…

Computation and Language · Computer Science 2021-07-27 Jiehang Zeng , Xiaoqing Zheng , Jianhan Xu , Linyang Li , Liping Yuan , Xuanjing Huang

Diffusion models have been applied to improve adversarial robustness of image classifiers by purifying the adversarial noises or generating realistic data for adversarial training. However, diffusion-based purification can be evaded by…

Computer Vision and Pattern Recognition · Computer Science 2024-05-22 Huanran Chen , Yinpeng Dong , Zhengyi Wang , Xiao Yang , Chengqi Duan , Hang Su , Jun Zhu

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

The unique characteristics of text data make classification tasks a complex problem. Advances in unsupervised and semi-supervised learning and autoencoder architectures addressed several challenges. However, they still struggle with…

Computation and Language · Computer Science 2024-10-30 Grigorii Khvatskii , Nuno Moniz , Khoa Doan , Nitesh V Chawla

Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…

Machine Learning · Computer Science 2020-12-21 Zhao Wang , Aron Culotta

It is well-known that classifiers are vulnerable to adversarial perturbations. To defend against adversarial perturbations, various certified robustness results have been derived. However, existing certified robustnesses are limited to…

Machine Learning · Computer Science 2019-12-23 Jinyuan Jia , Xiaoyu Cao , Binghui Wang , Neil Zhenqiang Gong

In this work, we propose a novel adversarial defence mechanism for image classification - CARSO - blending the paradigms of adversarial training and adversarial purification in a synergistic robustness-enhancing way. The method builds upon…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Emanuele Ballarin , Alessio Ansuini , Luca Bortolussi

Two fundamental problems in unsupervised learning are efficient inference for latent-variable models and robust density estimation based on large amounts of unlabeled data. Algorithms for the two tasks, such as normalizing flows and…

Machine Learning · Statistics 2018-08-02 Changyou Chen , Chunyuan Li , Liqun Chen , Wenlin Wang , Yunchen Pu , Lawrence Carin

This work studies the robust evaluation of iterative stochastic purification defenses under white-box adversarial attacks. Our key technical insight is that gradient checkpointing makes exact end-to-end gradient computation through long…

Machine Learning · Computer Science 2026-05-08 Yuan Du , Mitchel Hill , HanQin Cai

Video recognition models remain vulnerable to adversarial attacks, while existing diffusion-based purification methods suffer from inefficient sampling and curved trajectories. Directly regressing clean videos from adversarial inputs often…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Duoxun Tang , Xueyi Zhang , Chak Hin Wang , Xi Xiao , Dasen Dai , Xinhang Jiang , Wentao Shi , Rui Li , Qing Li

Recent work has proposed several efficient approaches for generating gradient-based adversarial perturbations on embeddings and proved that the model's performance and robustness can be improved when they are trained with these contaminated…

Computation and Language · Computer Science 2021-09-15 Yao Qiu , Jinchao Zhang , Jie Zhou

Representation learning of textual networks poses a significant challenge as it involves capturing amalgamated information from two modalities: (i) underlying network structure, and (ii) node textual attributes. For this, most existing…

Computation and Language · Computer Science 2020-11-06 Tony Gracious , Ambedkar Dukkipati

Neural networks are susceptible to data inference attacks such as the model inversion attack and the membership inference attack, where the attacker could infer the reconstruction and the membership of a data sample from the confidence…

Cryptography and Security · Computer Science 2020-08-21 Ziqi Yang , Bin Shao , Bohan Xuan , Ee-Chien Chang , Fan Zhang

Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data augmentation with…

Machine Learning · Computer Science 2024-05-28 Jieren Deng , Hanbin Hong , Aaron Palmer , Xin Zhou , Jinbo Bi , Kaleel Mahmood , Yuan Hong , Derek Aguiar

Recent studies on adversarial images have shown that they tend to leave the underlying low-dimensional data manifold, making them significantly more challenging for current models to make correct predictions. This so-called off-manifold…

Computation and Language · Computer Science 2022-11-08 Dang Minh Nguyen , Luu Anh Tuan

We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm. This "randomized smoothing" technique has been proposed…

Machine Learning · Computer Science 2019-06-18 Jeremy M Cohen , Elan Rosenfeld , J. Zico Kolter

The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's…

Cryptography and Security · Computer Science 2026-01-06 David D. Nguyen , The-Anh Ta , Yansong Gao , Alsharif Abuadbba