
Minmax in array
Given an array v of n numbers, where n=2k, k>0 be a natural number, find the minimum and maximum element in v. There are no assumptions regarding the orders of the elements of v. A basic iterative approach would require 2(n1) comparisons (n1 comparisons to find the minimum and n1 comparisons to find the maximum). However, your program MUST perform at most 3/2n1 comparisons. Difficulty:… Read more Continue reading Minmax in array

Kth smallest element in unsorted array
Given an array v of distinct numbers, and a number k where k is smaller than the size of v, find the kth smallest element in the array. A simple solution would be first sorting the array in growing order and than selecting the kth element which can be done in θ(n logn). However, your program MUST run in θ(n) on average. Difficulty: Medium. Input There… Read more Continue reading Kth smallest element in unsorted array

Adversarial policies: attacking TicTacToe multiagent environment
In a previous post we discussed about the possibility for an attacker to fool image classification models by injecting adversarial noise directly to the input images. Similarly, in this post we are going to see how is it possible to attack deep reinforcements learning agents on multiagent environments (where two or more agents interact within the same environment) such that one or more agents are… Read more Continue reading Adversarial policies: attacking TicTacToe multiagent environment

Defence methods for image adversarial attacks
In the previous post we reviewed some wellknown methods for blackbox decisionbased adversarial attacks where the adversary has no knowledge about the victim model except for its discrete hardlabel predictions, thus gradientbased methods become ineffective but simple randomwalk based methods such as the Boundary Attack can still represent a threat even under these particular settings. Now that we have introduced both white and blackbox attacks… Read more Continue reading Defence methods for image adversarial attacks

Blackbox decisionbased attacks on images
In the previous post we reviewed a series of blackbox scorebased adversarial attacks where the adversary has to estimate the gradient by querying the target model and retrieving the labels’ confidence score. In this post we are going to explore the third category of blackbox attacks, namely, blackbox decisionbased attacks. Under this settings, the only knowledge the attacker has about the model are only discrete… Read more Continue reading Blackbox decisionbased attacks on images

Blackbox scorebased attacks on images
In the previous post we reviewed a series of blackbox transferbased adversarial attacks where the adversary has to generate adversarial examples against a substitute model. In this post we are going to explore the second category of blackbox attacks, namely, blackbox scorebased attacks. Under this setting, it is not possible to access to the whitebox model’s gradients. The only knowledge about the attacked model are… Read more Continue reading Blackbox scorebased attacks on images

Blackbox transferbased attacks on images
In the previous post we reviewed a series of whitebox adversarial attacks where the adversary has full access and knowledge of the victim model. In this post we are going to explore the first category of blackbox attacks, namely, blackbox transferbased attacks. Transferbased attacks generate adversarial examples against a substitute model, possibly being as much similar as possible to the target model, which have a… Read more Continue reading Blackbox transferbased attacks on images