Related papers: Single Image Backdoor Inversion via Robust Smoothe…
Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly…
The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.…
Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…
Any classifier can be "smoothed out" under Gaussian noise to build a new classifier that is provably robust to $\ell_2$-adversarial perturbations, viz., by averaging its predictions over the noise via randomized smoothing. Under the…
We propose a stealthy clean-label video backdoor attack against Deep Learning (DL)-based models aiming at detecting a particular class of spoofing attacks, namely video rebroadcast attacks. The injected backdoor does not affect spoofing…
Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…
Organisations with limited data and computational resources increasingly outsource model training to Machine Learning as a Service (MLaaS) providers, who adapt vision-language models (VLMs) such as CLIP to downstream tasks via prompt tuning…
Under a commonly-studied backdoor poisoning attack against classification models, an attacker adds a small trigger to a subset of the training data, such that the presence of this trigger at test time causes the classifier to always predict…
When an inverse problem is solved by a gradient-based optimization algorithm, the corresponding forward and adjoint problems, which are introduced to compute the gradient, can be also solved iteratively. The idea of iterating at the same…
Deep Neural Networks (DNNs) are vulnerable to backdoor attacks. Due to the nature of Machine Learning as a Service (MLaaS) applications, black-box defenses are more practical than white-box methods, yet existing purification techniques…
Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tasks. In this paper, we identify a novel security threat…
Randomness supports many critical functions in the field of machine learning (ML) including optimisation, data selection, privacy, and security. ML systems outsource the task of generating or harvesting randomness to the compiler, the cloud…
Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being proposed, successively or concurrently, in the status of a rapid arms…
Deep Neural Networks (DNNs) have been widely used in many areas such as autonomous driving and face recognition. However, DNN model is fragile to backdoor attack. A backdoor in the DNN model can be activated by a poisoned input with trigger…
Deep neural networks (DNNs) have gain its popularity in various scenarios in recent years. However, its excellent ability of fitting complex functions also makes it vulnerable to backdoor attacks. Specifically, a backdoor can remain hidden…
Over the past few years, the emergence of backdoor attacks has presented significant challenges to deep learning systems, allowing attackers to insert backdoors into neural networks. When data with a trigger is processed by a backdoor…
As society grows more reliant on machine learning, ensuring the security of machine learning systems against sophisticated attacks becomes a pressing concern. A recent result of Goldwasser, Kim, Vaikuntanathan, and Zamir (2022) shows that…
Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the training…
Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…
Recent progress in text-to-image (T2I) models enables high-quality image generation with flexible textual control. To utilize the abundant visual priors in the off-the-shelf T2I models, a series of methods try to invert an image to proper…