相关论文: Evading Data Provenance in Deep Neural Networks

Deep learning (DL) has shown great success in many human-related tasks, which has led to its adoption in many computer vision based applications, such as security surveillance systems, autonomous vehicles and healthcare. Such…

Machine learning models, especially deep models, may unintentionally remember information about their training data. Malicious attackers can thus pilfer some property about training data by attacking the model via membership inference…

Existing deep learning approaches for learning visual features tend to overlearn and extract more information than what is required for the task at hand. From a privacy preservation perspective, the input visual information is not protected…

Detecting out-of-distribution (OOD) instances is crucial for the reliable deployment of machine learning models in real-world scenarios. OOD inputs are commonly expected to cause a more uncertain prediction in the primary task; however,…

Data-driven methods have been widely used in network intrusion detection (NID) systems. However, there are currently a number of challenges derived from how the datasets are being collected. Most attack classes in network intrusion datasets…

Substantial progress has been made in various techniques for open-world recognition. Out-of-distribution (OOD) detection methods can effectively distinguish between known and unknown classes in the data, while incremental learning enables…

The rise of Machine Learning as a Service (MLaaS) has led to the widespread deployment of machine learning models trained on diverse datasets. These models are employed for predictive services through APIs, raising concerns about the…

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…

Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such attacks is critical in order to ensure the safety and robustness of critical AI…

With the increasing deployment of deep neural networks in safety-critical applications such as self-driving cars, medical imaging, anomaly detection, etc., adversarial robustness has become a crucial concern in the reliability of these…

Deep neural networks (DNNs) and generative AI (GenAI) are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks, including evasion and backdoor (poisoning) attacks. On the defense side, there have been intensive efforts on improving both empirical and…

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently lead to high-confidence predictions for OOD samples. This…

Large Language Models (LLMs) have transformed natural language processing by learning from massive datasets, yet this rapid progress has also drawn legal scrutiny, as the ability to unintentionally generate copyrighted content has already…

We present Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch. State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets…

Unsupervised Outlier Detection (UOD) is a critical task in data mining and machine learning, aiming to identify instances that significantly deviate from the majority. Without any label, deep UOD methods struggle with the misalignment…

A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small number of samples that each possess the backdoor pattern (usually…

Ensuring the reliability and safety of machine learning models in open-world deployment is a central challenge in AI safety. This thesis develops both algorithmic and theoretical foundations to address key reliability issues arising from…

Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution (OOD) inputs. This limitation is one of the key challenges in the adoption of deep learning models in high-assurance…

The rapid expansion of data from diverse sources has made anomaly detection (AD) increasingly essential for identifying unexpected observations that may signal system failures, security breaches, or fraud. As datasets become more complex…