Related papers: dataRLsec: Safety, Security, and Reliability With …
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…
Ramp metering is the act of controlling on-going vehicles to the highway mainlines. Decades of practices of ramp metering have proved that ramp metering can decrease total travel time, mitigate shockwaves, decrease rear-end collisions by…
The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…
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…
With the widespread adoption of deep learning, reinforcement learning (RL) has experienced a dramatic increase in popularity, scaling to previously intractable problems, such as playing complex games from pixel observations, sustaining…
LoRa provides long-range, energy-efficient communications in Internet of Things (IoT) applications that rely on Low-Power Wide-Area Network (LPWAN) capabilities. Despite these merits, concerns persist regarding the security of LoRa…
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…
Most offline reinforcement learning (RL) algorithms return a target policy maximizing a trade-off between (1) the expected performance gain over the behavior policy that collected the dataset, and (2) the risk stemming from the…
Currently, reinforcement learning (RL), especially deep RL, has received more and more attention in the research area. However, the security of RL has been an obvious problem due to the attack manners becoming mature. In order to defend…
One of the key challenges to deep reinforcement learning (deep RL) is to ensure safety at both training and testing phases. In this work, we propose a novel technique of unsupervised action planning to improve the safety of on-policy…
The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates a cooperative backdoor attack in a decentralized…
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…
Deep Reinforcement Learning (DRL) algorithms have recently made significant strides in improving network performance. Nonetheless, their practical use is still limited in the absence of safe exploration and safe decision-making. In the…
Data poisoning considers an adversary that distorts the training set of machine learning algorithms for malicious purposes. In this work, we bring to light one conjecture regarding the fundamentals of data poisoning, which we call the…
The scale of Internet-connected systems has increased considerably, and these systems are being exposed to cyber attacks more than ever. The complexity and dynamics of cyber attacks require protecting mechanisms to be responsive, adaptive,…
Reinforcement learning (RL) is one of the most important branches of AI. Due to its capacity for self-adaption and decision-making in dynamic environments, reinforcement learning has been widely applied in multiple areas, such as…
Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…
The success of deep reinforcement learning (DRL) hinges on the availability of training data, which is typically obtained via a large number of environment interactions. In many real-world scenarios, costs and risks are associated with…
Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement learning algorithms such as Proximal Policy Optimization…
Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs), in which an attacker…