Related papers: Temporary Power Adjusting Withholding Attack

We study a security threat to adversarial multi-armed bandits, in which an attacker perturbs the loss or reward signal to control the behavior of the victim bandit player. We show that the attacker is able to mislead any no-regret…

I study adversarial attacks against stochastic bandit algorithms. At each round, the learner chooses an arm, and a stochastic reward is generated. The adversary strategically adds corruption to the reward, and the learner is only able to…

This paper investigates stochastic multi-armed bandit algorithms that are robust to adversarial attacks, where an attacker can first observe the learner's action and {then} alter their reward observation. We study two cases of this model,…

This paper integrates Austrian capital theory with repeated game theory to examine strategic miner behaviour under different institutional conditions in blockchain systems. It shows that when protocol rules are mutable, effective time…

We consider the setting of online convex optimization with adversarial time-varying constraints in which actions must be feasible w.r.t. a fixed constraint set, and are also required on average to approximately satisfy additional…

In this paper, we review the undercutting attacks in the transaction-fee-based regime of proof-of-work (PoW) blockchains with the longest chain fork-choice rule. Next, we focus on the problem of fluctuations in mining revenue and the mining…

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

Deep learning has achieved remarkable success in direction-of-arrival (DOA) estimation. However, recent studies have shown that adversarial perturbations can severely compromise the performance of such models. To address this vulnerability,…

Engagement-optimized adaptive tutoring systems may prioritize short-term behavioral signals over sustained learning outcomes, creating structural incentives for reward hacking in reinforcement learning policies. We formalize this challenge…

The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. This issue becomes severe in high-dimensional state, where the…

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of…

Stochastic multi-armed bandits form a class of online learning problems that have important applications in online recommendation systems, adaptive medical treatment, and many others. Even though potential attacks against these learning…

Proof of Work (PoW) blockchains are susceptible to adversarial majority mining attacks in the early stages due to incipient participation and corresponding low net hash power. Bootstrapping ensures safety and liveness during the transient…

Temporal Key Integrity Protocol (TKIP) is a provisional solution for Wired Equivalent Privacy (WEP) security loopholes present in already widely deployed legacy 802.11 wireless devices. In this work, we model and analyse the computational…

This paper considers the problem of distributed bandit online convex optimization with time-varying coupled inequality constraints. This problem can be defined as a repeated game between a group of learners and an adversary. The learners…

Imposing fairness in resource allocation incurs a loss of system throughput, known as the Price of Fairness ($PoF$). In wireless scheduling, $PoF$ increases when serving users with very poor channel quality because the scheduler wastes…

The protocol for cryptocurrencies can be divided into three parts, namely consensus, wallet, and networking overlay. The aim of the consensus part is to bring trustless rational peer-to-peer nodes to an agreement to the current status of…

Fragmentation of expensive resources, e.g., spectrum for wireless services, between providers can introduce inefficiencies in resource utilisation and worsen overall system performance. In such cases, resource pooling between independent…

State-of-the-art reinforcement learning (RL) algorithms typically use random sampling (e.g., $\epsilon$-greedy) for exploration, but this method fails on hard exploration tasks like Montezuma's Revenge. To address the challenge of…

Most cryptocurrencies rely on Proof-of-Work (PoW) "mining" for resistance to Sybil and double-spending attacks, as well as a mechanism for currency issuance. Hashcash PoW has successfully secured the Bitcoin network since its inception,…