Related papers: PoisonedEncoder: Poisoning the Unlabeled Pre-train…

Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…

Semi-supervised machine learning (SSL) is gaining popularity as it reduces the cost of training ML models. It does so by using very small amounts of (expensive, well-inspected) labeled data and large amounts of (cheap, non-inspected)…

Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There are two prevalent approaches for this, contrastive learning…

Deep neural network (DNN) classifiers are vulnerable to backdoor attacks. An adversary poisons some of the training data in such attacks by installing a trigger. The goal is to make the trained DNN output the attacker's desired class…

Supervised learning is based on the assumption that the ground truth in the training data is accurate. However, this may not be guaranteed in real-world settings. Inaccurate training data will result in some unexpected predictions. In image…

Although one-hot encoding is commonly used for multiclass classification, it is not always the most effective encoding mechanism. Error Correcting Output Codes (ECOC) address multiclass classification by mapping each class to a unique…

We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pre-trained…

Contrastive vision-language representation learning has achieved state-of-the-art performance for zero-shot classification, by learning from millions of image-caption pairs crawled from the internet. However, the massive data that powers…

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor…

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been…

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

This is Btech thesis report on detection and purification of adverserially attacked images. A deep learning model is trained on certain training examples for various tasks such as classification, regression etc. By training, weights are…

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…

Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference. A recent survey of industry practitioners found that data poisoning is the number one concern among threats ranging from model…

Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of…

Federated Contrastive Learning (FCL) is an emerging privacy-preserving paradigm in distributed learning for unlabeled data. In FCL, distributed parties collaboratively learn a global encoder with unlabeled data, and the global encoder could…

We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error. Inspired by the observation that linear…

This paper investigates poisoning attacks against data-driven control methods. This work is motivated by recent trends showing that, in supervised learning, slightly modifying the data in a malicious manner can drastically deteriorate the…

Self-Supervised Learning (SSL) is an effective paradigm for learning representations from unlabeled data, such as text, images, and videos. However, researchers have recently found that SSL is vulnerable to backdoor attacks. The attacker…