相关论文: Silent Killer: A Stealthy, Clean-Label, Black-Box …

We demonstrate a backdoor attack on a deep neural network used for regression. The backdoor attack is localized based on training-set data poisoning wherein the mislabeled samples are surrounded by correctly labeled ones. We demonstrate how…

Self-supervised contrastive learning (CL) effectively learns transferable representations from unlabeled data containing images or image-text pairs but suffers vulnerability to data poisoning backdoor attacks (DPCLs). An adversary can…

Quantum Machine Learning (QML) integrates quantum computational principles into learning algorithms, offering improved representational capacity and computational efficiency. However, the security and robustness of QML systems remain…

Since 2014 when Szegedy et al. showed that carefully designed perturbations of the input can lead Deep Neural Networks (DNNs) to wrongly classify its label, there has been an ongoing research to make DNNs more robust to such malicious…

Backdoor attacks embed hidden associations between triggers and targets in deep neural networks (DNNs), causing them to predict the target when a trigger is present while maintaining normal behavior otherwise. Physical backdoor attacks,…

Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…

Recent studies have demonstrated the susceptibility of deep neural networks to backdoor attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be dominated by the trigger information, though trigger…

Widely used deep learning models are found to have poor robustness. Little noises can fool state-of-the-art models into making incorrect predictions. While there is a great deal of high-performance attack generation methods, most of them…

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…

Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…

Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic…

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

We study black-box reward poisoning attacks against reinforcement learning (RL), in which an adversary aims to manipulate the rewards to mislead a sequence of RL agents with unknown algorithms to learn a nefarious policy in an environment…

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Knowledge distillation has become a cornerstone in modern machine learning systems, celebrated for its ability to transfer knowledge from a large, complex teacher model to a more efficient student model. Traditionally, this process is…

Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data. However, previous studies have revealed that such models are vulnerable to backdoor…

Backdoor attack against deep neural networks is currently being profoundly investigated due to its severe security consequences. Current state-of-the-art backdoor attacks require the adversary to modify the input, usually by adding a…

Since DNN is vulnerable to carefully crafted adversarial examples, adversarial attack on LiDAR sensors have been extensively studied. We introduce a robust black-box attack dubbed LiDAttack. It utilizes a genetic algorithm with a simulated…

Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…

Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the true class label, we…