Related papers: On Robustness of Linear Classifiers to Targeted Da…
Emerging technologies drive the ongoing transformation of Intelligent Transportation Systems (ITS). This transformation has given rise to cybersecurity concerns, among which data poisoning attack emerges as a new threat as ITS increasingly…
Data-driven control has emerged as a powerful paradigm for synthesizing controllers directly from data, bypassing explicit model identification. However, this reliance on data introduces new and largely unexplored vulnerabilities. In this…
Given the volume of data needed to train modern machine learning models, external suppliers are increasingly used. However, incorporating external data poses data poisoning risks, wherein attackers manipulate their data to degrade model…
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…
Model inversion attacks pose a significant privacy threat to machine learning models by reconstructing sensitive data from their outputs. While various defenses have been proposed to counteract these attacks, they often come at the cost of…
Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to confuse the model into making a mistake. Such examples pose a serious threat to the applicability of machine-learning-based systems,…
The concept of learned index structures relies on the idea that the input-output functionality of a database index can be viewed as a prediction task and, thus, be implemented using a machine learning model instead of traditional…
Test-time adaptation (TTA) updates the model weights during the inference stage using testing data to enhance generalization. However, this practice exposes TTA to adversarial risks. Existing studies have shown that when TTA is updated with…
The widespread adoption of generative models such as Stable Diffusion and ChatGPT has made them increasingly attractive targets for malicious exploitation, particularly through data poisoning. Existing poisoning attacks compromising…
Targeted data poisoning (TDP) aims to compromise the model's prediction on a specific (test) target by perturbing a small subset of training data. Existing work on TDP has focused on an overly ideal threat model in which the same image…
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…
This paper establishes a mathematically precise definition of dataset poisoning attack and proves that the very act of effectively poisoning a dataset ensures that the attack can be effectively detected. On top of a mathematical guarantee…
Machine learning is becoming ubiquitous. From finance to medicine, machine learning models are boosting decision-making processes and even outperforming humans in some tasks. This huge progress in terms of prediction quality does not…
We use distributionally-robust optimization for machine learning to mitigate the effect of data poisoning attacks. We provide performance guarantees for the trained model on the original data (not including the poison records) by training…
Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…
As machine learning models become increasingly complex, concerns about their robustness and trustworthiness have become more pressing. A critical vulnerability of these models is data poisoning attacks, where adversaries deliberately alter…
Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…
Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect…
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 study defense strategies against reward poisoning attacks in reinforcement learning. As a threat model, we consider attacks that minimally alter rewards to make the attacker's target policy uniquely optimal under the poisoned rewards,…