Related papers: Addressing The Devastating Effects Of Single-Task …
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process,…
Similar to other machine learning frameworks, Offline Reinforcement Learning (RL) is shown to be vulnerable to poisoning attacks, due to its reliance on externally sourced datasets, a vulnerability that is exacerbated by its sequential…
A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction…
Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to…
Federated Learning (FL) is a decentralized machine learning method that enables participants to collaboratively train a model without sharing their private data. Despite its privacy and scalability benefits, FL is susceptible to backdoor…
The perturbation analysis of linear solvers applied to systems arising broadly in machine learning settings -- for instance, when using linear regression models -- establishes an important perspective when reframing these analyses through…
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…
Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small, concealed changes to the training data. In this work, we…
Adversarial training (AT) is a robust learning algorithm that can defend against adversarial attacks in the inference phase and mitigate the side effects of corrupted data in the training phase. As such, it has become an indispensable…
Adversarial attacks such as poisoning attacks have attracted the attention of many machine learning researchers. Traditionally, poisoning attacks attempt to inject adversarial training data in order to manipulate the trained model. In…
Federated learning (FL) has become a popular tool for solving traditional Reinforcement Learning (RL) tasks. The multi-agent structure addresses the major concern of data-hungry in traditional RL, while the federated mechanism protects the…
Poisoning attacks are a primary threat to machine learning models, aiming to compromise their performance and reliability by manipulating training datasets. This paper introduces a novel attack - Outlier-Oriented Poisoning (OOP) attack,…
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…
We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…
Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a…
Machine learning is susceptible to poisoning attacks, in which an attacker controls a small fraction of the training data and chooses that data with the goal of inducing some behavior unintended by the model developer in the trained model.…
Federated learning (FL) combined with local differential privacy (LDP) enables privacy-preserving model training across decentralized data sources. However, the decentralized data-management paradigm leaves LDPFL vulnerable to participants…
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…
Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…
There has been recent interest in leveraging federated learning (FL) for radio signal classification tasks. In FL, model parameters are periodically communicated from participating devices, training on their own local datasets, to a central…