Search Results for author:
Found 17 papers, 6 papers with code
BridgePure: Revealing the Fragility of Black-box Data Protection
Availability attacks, or unlearnable examples, are defensive techniques that allow data owners to modify their datasets in ways that prevent unauthorized machine learning models from learning effectively while maintaining the data's intended functionality.
Explaining Non-monotonic Normative Reasoning using Argumentation Theory with Deontic Logic
Building on this, this paper explores how to provide designers with effective explanations for their legally relevant design decisions.
Machine Unlearning Fails to Remove Data Poisoning Attacks
We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning.
Alignment Calibration: Machine Unlearning for Contrastive Learning under Auditing
Machine unlearning provides viable solutions to revoke the effect of certain training data on pre-trained model parameters.
Disguised Copyright Infringement of Latent Diffusion Models
Copyright infringement may occur when a generative model produces samples substantially similar to some copyrighted data that it had access to during the training phase.
Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers
In neural network binarization, BinaryConnect (BC) and its variants are considered the standard.
Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors
In this paper, we extend the exploration of the threat of indiscriminate attacks on downstream tasks that apply pre-trained feature extractors.
$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning
In self-supervised contrastive learning, a widely-adopted objective function is InfoNCE, which uses the heuristic cosine similarity for the representation comparison, and is closely related to maximizing the Kullback-Leibler (KL)-based mutual information.
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
Building on existing parameter corruption attacks and refining the Gradient Canceling attack, we perform extensive experiments to confirm our theoretical findings, test the predictability of our transition threshold, and significantly improve existing indiscriminate data poisoning baselines over a range of datasets and models.
An Argumentation-Based Legal Reasoning Approach for DL-Ontology
Ontology is a popular method for knowledge representation in different domains, including the legal domain, and description logics (DL) is commonly used as its description language.
Indiscriminate Data Poisoning Attacks on Neural Networks
Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention.
$f$-Mutual Information Contrastive Learning
Self-supervised contrastive learning is an emerging field due to its power in providing good data representations.
AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
In particular, we propose a new problem called unlabeled scene-adaptive crowd counting.
Few-shot Scene-adaptive Anomaly Detection
In this paper, we propose a novel few-shot scene-adaptive anomaly detection problem to address the limitations of previous approaches.
Structure Learning with Similarity Preserving
Leveraging on the underlying low-dimensional structure of data, low-rank and sparse modeling approaches have achieved great success in a wide range of applications.
Future Frame Prediction Using Convolutional VRNN for Anomaly Detection
Anomaly detection in videos aims at reporting anything that does not conform the normal behaviour or distribution.
Similarity Learning via Kernel Preserving Embedding
Data similarity is a key concept in many data-driven applications.
