相关论文: Multi-level Certified Defense Against Poisoning At…

Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female. Recently, fair representation learning (FRL) trained by deep neural networks has demonstrated superior…

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

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…

In offline reinforcement learning (RL), we learn policies from fixed datasets without environment interaction. The major challenges are to provide guarantees on the (1) performance and (2) safety of the resulting policy. A technique called…

Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…

Offline reinforcement learning (RL) allows for the training of competent agents from offline datasets without any interaction with the environment. Online finetuning of such offline models can further improve performance. But how should we…

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various…

Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the environment. We aim to tackle a more challenging problem: learning a safe policy from an offline dataset. We study the offline safe RL problem…

In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a…

Constrained reinforcement learning (RL) seeks high-performance policies under safety constraints. We focus on an offline setting where the agent has only a fixed dataset -- common in realistic tasks to prevent unsafe exploration. To address…

Offline reinforcement learning (RL) aims to optimize the return given a fixed dataset of agent trajectories without additional interactions with the environment. While algorithm development has progressed rapidly, significant theoretical…

Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we…

This paper investigates the critical issue of data poisoning attacks on AI models, a growing concern in the ever-evolving landscape of artificial intelligence and cybersecurity. As advanced technology systems become increasingly prevalent…

Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities extend to deep…

Federated Learning (FL) is a distributed machine learning diagram that enables multiple clients to collaboratively train a global model without sharing their private local data. However, FL systems are vulnerable to attacks that are…

Federated learning (FL) provides a high efficient decentralized machine learning framework, where the training data remains distributed at remote clients in a network. Though FL enables a privacy-preserving mobile edge computing framework…

Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an offline dataset and subsequently deploying them in an online…

Post-training algorithms based on deep reinforcement learning can push the limits of robotic models for specific objectives, such as generalizability, accuracy, and robustness. However, Intervention-requiring Failures (IR Failures) (e.g., a…

We consider the offline reinforcement learning problem, where the aim is to learn a decision making policy from logged data. Offline RL -- particularly when coupled with (value) function approximation to allow for generalization in large or…

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…