Related papers: Temporary Power Adjusting Withholding Attack
Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more…
We do not know how to align a very intelligent AI agent's behavior with human interests. I investigate whether -- absent a full solution to this AI alignment problem -- we can build smart AI agents which have limited impact on the world,…
Bandit Convex Optimization is a fundamental class of sequential decision-making problems, where the learner selects actions from a continuous domain and observes a loss (but not its gradient) at only one point per round. We study this…
Balancing strong privacy guarantees with high predictive performance is critical for time series forecasting (TSF) tasks involving Electronic Health Records (EHR). In this study, we explore how data augmentation can mitigate Membership…
We study the constrained variant of the \emph{multi-armed bandit} (MAB) problem, in which the learner aims not only at minimizing the total loss incurred during the learning dynamic, but also at controlling the violation of multiple…
Bitcoin's price has been described as following a power law (PL) in time, $P \sim t^{\beta}$ with $\hat\beta \approx 5.7$ over 2010-2026. We test this claim using the Clauset-Shalizi-Newman protocol applied to Bitcoin's tail-relevant…
In a PoW-based blockchain network, mining pools (the solo miner could be regarded as a mining pool containing one miner) compete to successfully mine blocks to pursue rewards. Generally, the rewards include the fixed block subsidies and…
Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks, yet effective defenses remain underexplored due to challenges arising from data entanglement and shifts in task formulation. To fill this gap, we conduct a systematic…
Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…
Proof-of-work (PoW) is an algorithmic tool used to secure networks by imposing a computational cost on participating devices. Unfortunately, traditional PoW schemes require that correct devices perform computational work perpetually, even…
Often, labeling large amount of data is challenging due to high labeling cost limiting the application domain of deep learning techniques. Active learning (AL) tackles this by querying the most informative samples to be annotated among…
We consider a novel stochastic multi-armed bandit setting, where playing an arm makes it unavailable for a fixed number of time slots thereafter. This models situations where reusing an arm too often is undesirable (e.g. making the same…
Iterative Direct Preference Optimization (DPO) has emerged as a widely used paradigm for aligning Large Language Models on reasoning tasks. Existing approaches typically rely on Best-of-N sampling ($N\geq8$) to mine positive trajectories…
We review the so called selfish mining strategy in the Bitcoin network and compare its profitability to honest mining.We build a rigorous profitability model for repetition games. The time analysis of the attack has been ignored in the…
Rollups have become the de facto scalability solution for Ethereum, securing more than $55B in assets. They achieve scale by executing transactions on a Layer 2 ledger, while periodically posting data and finalizing state on the Layer 1,…
Proof-of-Stake (PoS) blockchain systems, especially those that allow stakeholders to organize themselves in ``stake-pools'', have emerged as a compelling paradigm for the deployment of large scale distributed ledgers. A stake-pool operates…
Adversarial training (AT) is widely considered as the most promising strategy to defend against adversarial attacks and has drawn increasing interest from researchers. However, the existing AT methods still suffer from two challenges.…
While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike execution-based tools (e.g., code or math), whose effects are…
Designing an efficient difficulty control algorithm is an essential problem in Proof-of-Work (PoW) based blockchains because the network hash rate is randomly changing. This paper proposes a general difficulty control algorithm and provides…
Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to mislead multiple…