相关论文: Robust Backdoor Detection for Deep Learning via To…

Deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to backdoor attacks.…

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…

Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks--most notably backdoor attacks. Existing KD…

Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data. The attacked model behaves normally on benign samples, whereas its prediction will be…

The rapid expansion of connected devices has made them prime targets for cyberattacks. To address these threats, deep learning-based, data-driven intrusion detection systems (IDS) have emerged as powerful tools for detecting and mitigating…

Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into models remain active indefinitely. In practice, models are…

In recent years, deep learning-based Monocular Depth Estimation (MDE) models have been widely applied in fields such as autonomous driving and robotics. However, their vulnerability to backdoor attacks remains unexplored. To fill the gap in…

Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant an undetectable backdoor into a…

Federated learning is a promising approach for training machine learning models while preserving data privacy. However, its distributed nature makes it vulnerable to backdoor attacks, particularly in NLP tasks, where related research…

Dataset distillation (DD) enhances training efficiency and reduces bandwidth by condensing large datasets into smaller synthetic ones. It enables models to achieve performance comparable to those trained on the raw full dataset and has…

Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a backdoor pattern is…

Federated learning allows multiple participants to collaboratively train a central model without sharing their private data. However, this distributed nature also exposes new attack surfaces. In particular, backdoor attacks allow attackers…

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

The remarkable success of pretrain-then-finetune paradigm has led to a proliferation of available pre-trained models for vision tasks. This surge presents a significant challenge in efficiently choosing the most suitable pre-trained models…

Object detection models, widely used in security-critical applications, are vulnerable to backdoor attacks that cause targeted misclassifications when triggered by specific patterns. Existing backdoor defense techniques, primarily designed…

Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences to detect such attacks. However, concealed backdoors evade…

Deep Reinforcement Learning (DRL) enhances the efficiency of Autonomous Vehicles (AV), but also makes them susceptible to backdoor attacks that can result in traffic congestion or collisions. Backdoor functionality is typically incorporated…

Deep neural networks are vulnerable to a range of adversaries. A particularly pernicious class of vulnerabilities are backdoors, where model predictions diverge in the presence of subtle triggers in inputs. An attacker can implant a…

Current backdoor attacks against federated learning (FL) strongly rely on universal triggers or semantic patterns, which can be easily detected and filtered by certain defense mechanisms such as norm clipping, comparing parameter…