English
Related papers

Related papers: How to Robustify Black-Box ML Models? A Zeroth-Ord…

200 papers

Implicit layer deep learning techniques, like Neural Differential Equations, have become an important modeling framework due to their ability to adapt to new problems automatically. Training a neural differential equation is effectively a…

Machine Learning · Computer Science 2023-06-05 Avik Pal , Alan Edelman , Chris Rackauckas

Countless domains rely on Machine Learning (ML) models, including safety-critical domains, such as autonomous driving, which this paper focuses on. While the black box nature of ML is simply a nuisance in some domains, in safety-critical…

Artificial Intelligence · Computer Science 2024-06-24 Lynn Vonderhaar , Timothy Elvira , Tyler Procko , Omar Ochoa

Deep Neural Networks (DNNs) in Computer Vision (CV) are well-known to be vulnerable to Adversarial Examples (AEs), namely imperceptible perturbations added maliciously to cause wrong classification results. Such variability has been a…

Cryptography and Security · Computer Science 2020-07-31 Yi Zeng , Han Qiu , Gerard Memmi , Meikang Qiu

Zeroth-order (ZO) optimization is a subset of gradient-free optimization that emerges in many signal processing and machine learning applications. It is used for solving optimization problems similarly to gradient-based methods. However, it…

Machine Learning · Computer Science 2020-06-23 Sijia Liu , Pin-Yu Chen , Bhavya Kailkhura , Gaoyuan Zhang , Alfred Hero , Pramod K. Varshney

Deep neural networks are susceptible to adversarial manipulations in the input domain. The extent of vulnerability has been explored intensively in cases of $\ell_p$-bounded and $\ell_p$-minimal adversarial perturbations. However, the…

Machine Learning · Computer Science 2019-10-10 Ali Dabouei , Sobhan Soleymani , Fariborz Taherkhani , Jeremy Dawson , Nasser M. Nasrabadi

As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the behaviors of these black boxes. However, existing…

Machine Learning · Computer Science 2020-11-13 Himabindu Lakkaraju , Nino Arsov , Osbert Bastani

A black-box spectral method is introduced for evaluating the adversarial robustness of a given machine learning (ML) model. Our approach, named SPADE, exploits bijective distance mapping between the input/output graphs constructed for…

Machine Learning · Computer Science 2021-06-15 Wuxinlin Cheng , Chenhui Deng , Zhiqiang Zhao , Yaohui Cai , Zhiru Zhang , Zhuo Feng

Given the widespread use of deep learning models in safety-critical applications, ensuring that the decisions of such models are robust against adversarial exploitation is of fundamental importance. In this thesis, we discuss recent…

Machine Learning · Computer Science 2025-09-24 Alexander Robey

Although deep generative models such as Defense-GAN and Defense-VAE have made significant progress in terms of adversarial defenses of image classification neural networks, several methods have been found to circumvent these defenses. Based…

Cryptography and Security · Computer Science 2020-11-04 Frederick Morlock , Dingsu Wang

Clustering models constitute a class of unsupervised machine learning methods which are used in a number of application pipelines, and play a vital role in modern data science. With recent advancements in deep learning -- deep clustering…

Machine Learning · Computer Science 2022-10-06 Anshuman Chhabra , Ashwin Sekhari , Prasant Mohapatra

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Machine Learning · Computer Science 2019-11-12 Bai Li , Changyou Chen , Wenlin Wang , Lawrence Carin

Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data, is not disclosed explicitly as it might contain proprietary…

Machine Learning · Statistics 2018-02-15 Seong Joon Oh , Max Augustin , Bernt Schiele , Mario Fritz

We present a novel approach for attacking black-box large language models (LLMs) by exploiting their ability to express confidence in natural language. Existing black-box attacks require either access to continuous model outputs like logits…

Cryptography and Security · Computer Science 2025-10-21 Jie Zhang , Meng Ding , Yang Liu , Jue Hong , Florian Tramèr

We propose a voting ensemble of models trained by using block-wise transformed images with secret keys for an adversarially robust defense. Key-based adversarial defenses were demonstrated to outperform state-of-the-art defenses against…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 MaungMaung AprilPyone , Hitoshi Kiya

As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreaking prompts that bypass moderation and alignment. Drawing from…

Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…

Machine Learning · Computer Science 2024-11-06 Junhao Dong , Xinghua Qu , Z. Jane Wang , Yew-Soon Ong

Deep neural networks (DNNs) have achieved remarkable success in diverse fields. However, it has been demonstrated that DNNs are very vulnerable to adversarial examples even in black-box settings. A large number of black-box attack methods…

Machine Learning · Computer Science 2022-03-29 Junjie Fu , Jian Sun , Gang Wang

Gradient-free/zeroth-order methods for black-box convex optimization have been extensively studied in the last decade with the main focus on oracle calls complexity. In this paper, besides the oracle complexity, we focus also on iteration…

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…

Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Scott Freitas , Shang-Tse Chen , Zijie J. Wang , Duen Horng Chau
‹ Prev 1 4 5 6 7 8 10 Next ›