相关论文: PureGen: Universal Data Purification for Train-Tim…

Large organizations such as social media companies continually release data, for example user images. At the same time, these organizations leverage their massive corpora of released data to train proprietary models that give them an edge…

This work studies the robust evaluation of iterative stochastic purification defenses under white-box adversarial attacks. Our key technical insight is that gradient checkpointing makes exact end-to-end gradient computation through long…

Regression models are widely used in industrial processes, engineering, and in natural and physical sciences, yet their robustness to poisoning has received less attention. When it has, studies often assume unrealistic threat models and are…

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…

Machine learning models are brittle, and small changes in the training data can result in different predictions. We study the problem of proving that a prediction is robust to data poisoning, where an attacker can inject a number of…

Backdoor attacks inject poisoned samples into the training data, resulting in the misclassification of the poisoned input during a model's deployment. Defending against such attacks is challenging, especially for real-world black-box models…

Federated learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to client-side data poisoning attacks (DPAs) and model poisoning attacks (MPAs) that degrade global model…

Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and similar algorithms, reduce the likelihood of harmful…

Data poisoning attacks pose significant threats to machine learning models by introducing malicious data into the training process, thereby degrading model performance or manipulating predictions. Detecting and sifting out poisoned data is…

With the increase in machine learning (ML) applications in different domains, incentives for deceiving these models have reached more than ever. As data is the core backbone of ML algorithms, attackers shifted their interest toward…

Poisoning attacks pose significant challenges to the robustness of diffusion models (DMs). In this paper, we systematically analyze when and where poisoning attacks textual inversion (TI), a widely used personalization technique for DMs. We…

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.…

Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise the network at the inference time by applying elaborately designed perturbation to…

It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusion models, a question naturally arises: can better diffusion…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted…

The performance of a machine learning-based malware classifier depends on the large and updated training set used to induce its model. In order to maintain an up-to-date training set, there is a need to continuously collect benign and…

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are…

Modern large language models (LLMs) exhibit critical vulnerabilities to poison pill attacks: localized data poisoning that alters specific factual knowledge while preserving overall model utility. We systematically demonstrate these attacks…