相关论文: Poisons that are learned faster are more effective

Sponge examples are test-time inputs optimized to increase energy consumption and prediction latency of deep networks deployed on hardware accelerators. By increasing the fraction of neurons activated during classification, these attacks…

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion requests, one often-cited potential application for unlearning…

The increasing access to data poses both opportunities and risks in deep learning, as one can manipulate the behaviors of deep learning models with malicious training samples. Such attacks are known as data poisoning. Recent advances in…

Adversarial data poisoning is an effective attack against machine learning and threatens model integrity by introducing poisoned data into the training dataset. So far, it has been studied mostly for classification, even though regression…

Adversarial attacks have only focused on changing the predictions of the classifier, but their danger greatly depends on how the class is mistaken. For example, when an automatic driving system mistakes a Persian cat for a Siamese cat, it…

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…

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number of poisoned samples, such as mislabeled samples from…

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…

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…

We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller which first estimates the dynamics and the rewards from a batch…

This work introduces a verification framework that provides both sound and complete guarantees for data poisoning attacks during neural network training. We formulate adversarial data manipulation, model training, and test-time evaluation…

Data-driven predictive control (DPC) is a feedback control method for systems with unknown dynamics. It repeatedly optimizes a system's future trajectories based on past input-output data. We develop a numerical method that computes…

Recently, various parameter-efficient fine-tuning (PEFT) strategies for application to language models have been proposed and successfully implemented. However, this raises the question of whether PEFT, which only updates a limited set of…

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…

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

Availability poisons exploit supervised learning (SL) algorithms by introducing class-related shortcut features in images such that models trained on poisoned data are useless for real-world datasets. Self-supervised learning (SSL), which…