相关论文: DAPI: Domain Adaptive Toxicity Probe Vector Interv…

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…

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…

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.…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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.…