Related papers: Temporary Power Adjusting Withholding Attack
Defending against adversarial examples remains an open problem. A common belief is that randomness at inference increases the cost of finding adversarial inputs. An example of such a defense is to apply a random transformation to inputs…
The practical Domain Adaptation (DA) tasks, e.g., Partial DA (PDA), open-set DA, universal DA, and test-time adaptation, have gained increasing attention in the machine learning community. In this paper, we propose a novel approach, dubbed…
Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the $\ell_0$ norm constraint, which can succeed by only modifying a few pixels of an image. Despite a…
Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. \textit{Probabilistic embeddings for actor-critic RL}…
In cryptocurrencies, the block reward is meant to serve as the incentive mechanism for miners to commit resources to create blocks and in effect secure the system. Existing systems primarily divide the reward in proportion to expended…
Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF), yet they remain vulnerable to reward hacking. Existing attacks mainly operate within the semantic space, constructing…
Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a…
The Projected Augmented Waves (PAW) method is based on a linear transformation between the pseudo wavefunctions and the all electron wavefunctions. To obtain high accuracy with this method, it is important that the local part of the linear…
Proof-of-Stake consensus protocols give rise to complex modeling challenges. We analyze the recently-updated Tezos Proof-of-Stake protocol and demonstrate that, under certain conditions, rational participants are incentivized to behave…
The Thresholding Bandit Problem (TBP) aims to find the set of arms with mean rewards greater than a given threshold. We consider a new setting of TBP, where in addition to pulling arms, one can also \emph{duel} two arms and get the arm with…
We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm,…
The multi-armed bandit formalism has been extensively studied under various attack models, in which an adversary can modify the reward revealed to the player. Previous studies focused on scenarios where the attack value either is bounded at…
Bitcoin is a "crypto currency", a decentralized electronic payment scheme based on cryptography. Bitcoin economy grows at an incredibly fast rate and is now worth some 10 billions of dollars. Bitcoin mining is an activity which consists of…
This study evaluates the robustness of Proof of Team Sprint (PoTS) against adversarial attacks through simulations, focusing on the attacker win rate and computational efficiency under varying team sizes (\( N \)) and attacker ratios (\(…
Consider $N$ players and $K$ games taking place simultaneously. Each of these games is modeled as a Tug-of-War (ToW) game where increasing the action of one player decreases the reward for all other players. Each player participates in only…
In 2021 Ethereum adjusted the transaction pricing mechanism by implementing EIP-1559, which introduces the base fee - a network fee that is burned and dynamically adjusts to the network demand. The authors of the Ethereum Improvement…
Current Transferable Adversarial Examples (TAE) are primarily generated by adding Adversarial Noise (AN). Recent studies emphasize the importance of optimizing Data Augmentation (DA) parameters along with AN, which poses a greater threat to…
Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. This defense ability, however, is challenged in this paper. We identify a novel…
In the network security domain, due to practical issues -- including imbalanced data and heterogeneous legitimate network traffic -- adversarial attacks in machine learning-based NIDSs have been viewed as attack packets misclassified as…
In this paper we explore several contexts where an adversary has an upper hand over the defender by using special hardware in an attack. These include password processing, hard-drive protection, cryptocurrency mining, resource sharing, code…