English
Related papers

Related papers: Explainability-Guided Defense: Attribution-Aware M…

200 papers

Rationalization models, which select a subset of input text as rationale-crucial for humans to understand and trust predictions-have recently emerged as a prominent research area in eXplainable Artificial Intelligence. However, most of…

Computation and Language · Computer Science 2024-09-20 Yuankai Zhang , Lingxiao Kong , Haozhao Wang , Ruixuan Li , Jun Wang , Yuhua Li , Wei Liu

Deep models, while being extremely versatile and accurate, are vulnerable to adversarial attacks: slight perturbations that are imperceptible to humans can completely flip the prediction of deep models. Many attack and defense mechanisms…

Machine Learning · Computer Science 2019-07-30 Kaiwen Wu , Yaoliang Yu

Neural networks have changed the way machines interpret the world. At their core, they learn by following gradients, adjusting their parameters step by step until they identify the most discriminant patterns in the data. This process gives…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Samarup Bhattacharya , Anubhab Bhattacharya , Abir Chakraborty

In this paper, we introduce a novel neural network training framework that increases model's adversarial robustness to adversarial attacks while maintaining high clean accuracy by combining contrastive learning (CL) with adversarial…

Machine Learning · Computer Science 2022-09-13 Adir Rahamim , Itay Naeh

In artificial intelligence (AI), the complexity of many models and processes surpasses human understanding, making it challenging to determine why a specific prediction is made. This lack of transparency is particularly problematic in…

Machine Learning · Statistics 2025-06-30 Alexandra Stadler , Werner G. Müller , Radoslav Harman

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…

Machine Learning · Computer Science 2020-07-07 Samuel Henrique Silva , Peyman Najafirad

As black-box machine learning models grow in complexity and find applications in high-stakes scenarios, it is imperative to provide explanations for their predictions. Although Local Interpretable Model-agnostic Explanations (LIME) [22] is…

Machine Learning · Computer Science 2023-11-28 Zeren Tan , Yang Tian , Jian Li

Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few years. Algorithm design of AT and its variants are focused on…

Machine Learning · Computer Science 2022-06-15 Kaustubh Sridhar , Souradeep Dutta , Ramneet Kaur , James Weimer , Oleg Sokolsky , Insup Lee

As machine learning models are increasingly deployed in safety-critical domains, visual explanation techniques have become essential tools for supporting transparency. In this work, we reveal a new class of attacks that compromise model…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Farhin Farhad Riya , Shahinul Hoque , Jinyuan Stella Sun , Olivera Kotevska

Machine learning models are increasingly used in critical applications but are mostly "black boxes" due to their lack of transparency. Local explanation approaches, such as LIME, address this issue by approximating the behavior of complex…

Machine Learning · Computer Science 2025-12-01 Krishna Khadka , Sunny Shree , Pujan Budhathoki , Yu Lei , Raghu Kacker , D. Richard Kuhn

The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications, such as justice system, drug/vaccination design, and medical diagnosis. Although there are effective methods to train…

Machine Learning · Computer Science 2022-07-14 Mohit Bajaj , Lingyang Chu , Vittorio Romaniello , Gursimran Singh , Jian Pei , Zirui Zhou , Lanjun Wang , Yong Zhang

Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. Attackers add carefully-crafted perturbations to input, where…

Machine Learning · Computer Science 2020-10-08 Ninghao Liu , Mengnan Du , Ruocheng Guo , Huan Liu , Xia Hu

Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…

Machine Learning · Computer Science 2024-06-04 Xiaoling Zhou , Wei Ye , Zhemg Lee , Rui Xie , Shikun Zhang

Pre-trained language models (PLMs) have driven substantial progress in natural language processing but remain vulnerable to adversarial attacks, raising concerns about their robustness in real-world applications. Previous studies have…

Computation and Language · Computer Science 2025-10-17 Yang Wang , Chenghao Xiao , Yizhi Li , Stuart E. Middleton , Noura Al Moubayed , Chenghua Lin

Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscalibrated predictions,…

Machine Learning · Computer Science 2021-12-15 Yao Qin , Xuezhi Wang , Alex Beutel , Ed H. Chi

The current landscape of defensive mechanisms for LLMs is fragmented and underdeveloped, unlike prior work on classifiers. To further promote adversarial robustness in LLMs, we propose Inverse Language Modeling (ILM), a unified framework…

Computation and Language · Computer Science 2025-10-03 Davide Gabrielli , Simone Sestito , Iacopo Masi

Machine learning is used more and more often for sensitive applications, sometimes replacing humans in critical decision-making processes. As such, interpretability of these algorithms is a pressing need. One popular algorithm to provide…

Machine Learning · Computer Science 2020-01-14 Damien Garreau , Ulrike von Luxburg

Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations…

Post hoc explanation methods, such as LIME and SHAP, provide interpretable insights into black-box classifiers and are increasingly used to assess model biases and generalizability. However, these methods are vulnerable to adversarial…

Machine Learning · Computer Science 2025-08-18 Sam Chauhan , Estelle Duguet , Karthik Ramakrishnan , Hugh Van Deventer , Jack Kruger , Ranjan Subbaraman

Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Paul Gavrikov , Janis Keuper
‹ Prev 1 3 4 5 6 7 10 Next ›