Related papers: Temporary Power Adjusting Withholding Attack
We consider availability data poisoning attacks, where an adversary aims to degrade the overall test accuracy of a machine learning model by crafting small perturbations to its training data. Existing poisoning strategies can achieve the…
A widespread security claim of the Bitcoin system, presented in the original Bitcoin white-paper, states that the security of the system is guaranteed as long as there is no attacker in possession of half or more of the total computational…
In recommender system or crowdsourcing applications of online learning, a human's preferences or abilities are often a function of the algorithm's recent actions. Motivated by this, a significant line of work has formalized settings where…
Fine-tuning APIs make frontier LLMs easy to customize, but they can also weaken safety alignment during fine-tuning. While prior work shows that benign supervised fine-tuning (SFT) can reduce refusal behavior, deployed fine-tuning pipelines…
Mining is a central operation of all proof-of-work (PoW) based cryptocurrencies. The vast majority of miners today participate in "mining pools" instead of "solo mining" in order to lower risk and achieve a more steady income. However, this…
A proof of work (PoW) blockchain protocol distributes rewards to its participants, called miners, according to their share of the total computational power. Sufficiently large miners can perform selfish mining - deviate from the protocol to…
This paper studies a fundamental problem regarding the security of blockchain PoW consensus on how the existence of multiple misbehaving miners influences the profitability of selfish mining. Each selfish miner (or attacker interchangeably)…
Blockchains have recently gained popularity thanks to their ability to record "digital truth". They are designed to keep persistence, security, and avoid attacks which is useful for many applications. However, they are still problematic in…
Recent works reveal that adversarial augmentation benefits the generalization of neural networks (NNs) if used in an appropriate manner. In this paper, we introduce Temporal Adversarial Augmentation (TA), a novel video augmentation…
Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…
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…
Counterfactuals, or modified inputs that lead to a different outcome, are an important tool for understanding the logic used by machine learning classifiers and how to change an undesirable classification. Even if a counterfactual changes a…
Parallel Proof-of-Work (PoW) protocols have been suggested in the literature to improve the safety guarantees, transaction throughput and confirmation latencies of Nakamoto consensus. In this work, we first consider the existing parallel…
Most PoW blockchain protocols operate with a simple mechanism whereby a threshold is set for each block and miners generate block hashes until one of those values falls below the threshold. Although largely effective, this mechanism…
The penalization method is a popular technique to provide particle swarm optimizers with the ability to handle constraints. The downside is the need of penalization coefficients whose settings are problem-specific. While adaptive…
Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement learning methods face challenges in striking the right…
Several attacks have been proposed against Proof-of-Work blockchains, which may increase the attacker's share of mining rewards (e.g., selfish mining, block withholding). A further impact of such attacks, which has not been considered in…
The selfish mining attack, arguably the most famous game-theoretic attack in blockchain, indicates that the Bitcoin protocol is not incentive-compatible. Most subsequent works mainly focus on strengthening the selfish mining strategy, thus…
Proof-of-Work (PoW) is a fundamental underlying technology behind most major blockchain cryptocurrencies. It has been previously pointed out that quantum devices provide a computational advantage in performing PoW in the context of Bitcoin.…
We study the multi-armed bandit (MAB) problem with composite and anonymous feedback. In this model, the reward of pulling an arm spreads over a period of time (we call this period as reward interval) and the player receives partial rewards…