相关论文: Generalizable Targeted Data Poisoning against Vary…

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Adversarial attacks induce misclassification by introducing subtle perturbations. Recently, diffusion models are applied to the image classifiers to improve adversarial robustness through adversarial training or by purifying adversarial…

While recent works have indicated that federated learning (FL) may be vulnerable to poisoning attacks by compromised clients, their real impact on production FL systems is not fully understood. In this work, we aim to develop a…

Privacy protection is an important research area, which is especially critical in this big data era. To a large extent, the privacy of visual classification data is mainly in the mapping between the image and its corresponding label, since…

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-tuning on poisoned data, even when safeguarded by moderation…

Unsupervised domain adaptation (UDA) enables cross-domain learning without target domain labels by transferring knowledge from a labeled source domain whose distribution differs from that of the target. However, UDA is not always successful…

A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical…

Federated learning is vulnerable to poisoning attacks by malicious adversaries. Existing methods often involve high costs to achieve effective attacks. To address this challenge, we propose a sybil-based virtual data poisoning attack, where…

Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency,…

Differential Privacy (DP) has become the gold standard for protecting individual privacy in data analytics, and the shuffle-DP model has attracted significant attention from both academia and industry due to its favorable balance between…

Federated learning (FL) is vulnerable to model poisoning attacks due to its distributed nature. The current defenses start from all user gradients (model updates) in each communication round and solve for the optimal aggregation gradients…

Federated machine learning which enables resource constrained node devices (e.g., mobile phones and IoT devices) to learn a shared model while keeping the training data local, can provide privacy, security and economic benefits by designing…

Without direct access to the client's data, federated learning (FL) is well-known for its unique strength in data privacy protection among existing distributed machine learning techniques. However, its distributive and iterative nature…

Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisoning attacks that optimize the amplitude of malicious…

Federated learning (FL) provides autonomy and privacy by design to participating peers, who cooperatively build a machine learning (ML) model while keeping their private data in their devices. However, that same autonomy opens the door for…

Adversarial attacks by malicious actors on machine learning systems, such as introducing poison triggers into training datasets, pose significant risks. The challenge in resolving such an attack arises in practice when only a subset of the…

Neural Radiance Fields (NeRFs) have recently emerged as a powerful tool for 3D scene representation and rendering. These data-driven models can learn to synthesize high-quality images from sparse 2D observations, enabling realistic and…

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realistic privacy attacks.…

Recently, Mahloujifar and Mahmoody (TCC'17) studied attacks against learning algorithms using a special case of Valiant's malicious noise, called $p$-tampering, in which the adversary gets to change any training example with independent…