English
Related papers

Related papers: DAPI: Domain Adaptive Toxicity Probe Vector Interv…

200 papers

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…

This paper describes a simple yet effective technique for refining a pretrained classifier network. The proposed AdCorDA method is based on modification of the training set and making use of the duality between network weights and layer…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Lulan Shen , Ali Edalati , Brett Meyer , Warren Gross , James J. Clark

In this paper we present a novel approach towards variance reduction for discretised diffusion processes. The proposed approach involves specially constructed control variates and allows for a significant reduction in the variance for the…

Probability · Mathematics 2017-09-19 Denis Belomestny , Stefan Häfner , Tigran Nagapetyan , Mikhail Urusov

In the case of an imbalance between positive and negative samples, hard negative mining strategies have been shown to help models learn more subtle differences between positive and negative samples, thus improving recognition performance.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-13 Jiahan Zhang , Dayong Tian

Many real-world machine learning tasks require outputs that satisfy hard constraints, such as physical conservation laws, structured dependencies in graphs, or column-level relationships in tabular data. Existing approaches rely either on…

Artificial Intelligence · Computer Science 2025-11-21 Pantelis Dogoulis , Fabien Bernier , Félix Fourreau , Karim Tit , Maxime Cordy

Deep neural network (DNN) models are wellknown to easily misclassify prediction results by using input images with small perturbations, called adversarial examples. In this paper, we propose a novel adversarial detector, which consists of a…

Computer Vision and Pattern Recognition · Computer Science 2022-02-08 Takayuki Osakabe , Maungmaung Aprilpyone , Sayaka Shiota , Hitoshi Kiya

Pre-trained Language Models (PLMs) may be poisonous with backdoors or bias injected by the suspicious attacker during the fine-tuning process. A core challenge of purifying potentially poisonous PLMs is precisely finding poisonous…

Computation and Language · Computer Science 2023-05-09 Zhiyuan Zhang , Deli Chen , Hao Zhou , Fandong Meng , Jie Zhou , Xu Sun

Backdoor attack has been considered as a serious security threat to deep neural networks (DNNs). Poisoned sample detection (PSD) that aims at filtering out poisoned samples from an untrustworthy training dataset has shown very promising…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Mingda Zhang , Mingli Zhu , Zihao Zhu , Baoyuan Wu

Typically a classifier trained on a given dataset (source domain) does not performs well if it is tested on data acquired in a different setting (target domain). This is the problem that domain adaptation (DA) tries to overcome and, while…

Machine Learning · Computer Science 2018-08-01 Silvia Bucci , Mohammad Reza Loghmani , Barbara Caputo

As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize on bias…

Computation and Language · Computer Science 2019-08-19 Apik Ashod Zorian , Chandra Shekar Bikkanur

Civilizations have tried to make drinking water safe to consume for thousands of years. The process of determining water contaminants has evolved with the complexity of the contaminants due to pesticides and heavy metals. The routine…

Quantitative Methods · Quantitative Biology 2025-04-28 Emile Anand , Charles Steinhardt , Martin Hansen

A persistent challenge in practical classification tasks is that labeled training sets are not always available. In particle physics, this challenge is surmounted by the use of simulations. These simulations accurately reproduce most…

High Energy Physics - Phenomenology · Physics 2018-07-25 Patrick T. Komiske , Eric M. Metodiev , Benjamin Nachman , Matthew D. Schwartz

Deep neural networks have played a crucial part in many critical domains, such as autonomous driving, face recognition, and medical diagnosis. However, deep neural networks are facing security threats from backdoor attacks and can be…

Cryptography and Security · Computer Science 2023-11-30 Jiyang Guan , Jian Liang , Ran He

Recent breakthroughs in Large Language Models (LLMs) have revealed remarkable generative capabilities and emerging self-regulatory mechanisms, including self-correction and self-rewarding. However, current detoxification techniques rarely…

Computation and Language · Computer Science 2026-01-21 Kaituo Zhang , Zhimeng Jiang , Na Zou

Training object detectors with only image-level annotations is very challenging because the target objects are often surrounded by a large number of background clutters. Many existing approaches tackle this problem through object proposal…

Computer Vision and Pattern Recognition · Computer Science 2017-08-08 Wenhui Jiang , Thuyen Ngo , B. S. Manjunath , Zhicheng Zhao , Fei Su

In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our Dynamic Guidance Adversarial Distillation (DGAD) framework…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Hyejin Park , Dongbo Min

Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Chaoyang Wang , Yunhai Tong

Bayesian decision theory advocates the Bayes classifier as the optimal approach for minimizing the risk in machine learning problems. Current deep learning algorithms usually solve for the optimal classifier by \emph{implicitly} estimating…

Machine Learning · Computer Science 2025-07-01 Chaoqun Du , Yulin Wang , Shiji Song , Gao Huang

In previous work, a novel supervised framework implementing a binary classifier was presented that obtained excellent results for side effect discovery. Interestingly, unique side effects were identified when different binary classifiers…

Machine Learning · Computer Science 2014-09-04 Jenna M. Reps , Uwe Aickelin , Jonathan M. Garibaldi

Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities.…

Machine Learning · Computer Science 2024-03-27 Seokhyeon Ha , Sunbeom Jung , Jungwoo Lee