Related papers: Multivalent "Attacker & Guard" Strategy for Target…
A common observation regarding adversarial attacks is that they mostly give rise to false activation at the penultimate layer to fool the classifier. Assuming that these activation values correspond to certain features of the input, the…
We studied polyelectrolyte adsorption on a repulsive charged surface by scaling analysis. At low ionic strength and low surface charge density in which a single polyelectrolyte is able to be adsorbed onto the surface, different regimes in…
This paper presents an algorithm to deploy a team of {\it free} guards equipped with omni-directional cameras for tracking a bounded speed intruder inside a simply-connected polygonal environment. The proposed algorithm partitions the…
Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attaching the adversarial…
In the seller-buyer setting on machine learning models, the seller generates different copies based on the original model and distributes them to different buyers, such that adversarial samples generated on one buyer's copy would likely not…
We realized and experimentally tested a conceptually new kind of electrically thin absorbers of electromagnetic waves. The idea is to utilize a single layer of precisely designed meta-atoms. This allows one to design an absorber with…
We propose a protection scheme of a superconducting microwave resonator to realize a hybrid quantum system, where cold neutral atoms are coupled with a single microwave photon through magnetic dipole interaction at an interface inductor.…
Multivalent binding employs multiple simultaneous supramolecular interactions, increasing avidity and selectivity compared with monovalent binding. While equilibrium aspects of multivalency are well characterized, non-equilibrium behavior…
A key challenge in Molecular Communications (MC) is low data transmission rates, which can be addressed by channel multiplexing techniques. One way to achieve channel multiplexing in MC is to leverage the diversity of different molecule…
In biomimetic and biological systems, interactions between surfaces are often mediated by adhesive molecules, nanoparticles, or colloids dispersed in the surrounding solution. We present here a general, statistical-mechanical model for two…
We consider a variant of the target defense problem in a planar conical environment where a single defender is tasked to capture a sequence of incoming attackers. The attackers' objective is to breach the target boundary without being…
This paper studies the deployment of joint moving target defense (MTD) and deception against multi-stage cyberattacks. Given the system equipped with MTD that randomizes between different configurations, we investigate how to allocate a…
Recently, adversarial attacks for diffusion models as well as their fine-tuning process have been developed rapidly. To prevent the abuse of these attack algorithms from affecting the practical application of diffusion models, it is…
Multi-label classification, which predicts a set of labels for an input, has many applications. However, multiple recent studies showed that multi-label classification is vulnerable to adversarial examples. In particular, an attacker can…
We address a problem of area protection in graph-based scenarios with multiple agents. The problem consists of two adversarial teams of agents that move in an undirected graph shared by both teams. Agents are placed in vertices of the…
This paper focuses on high-transferable adversarial attacks on detectors, which are hard to attack in a black-box manner, because of their multiple-output characteristics and the diversity across architectures. To pursue a high attack…
Molecular Communications (MC) uses molecules as information carriers between nanomachines. MC channel in practice can be crowded with different types of molecules, i.e., ligands, which can have similar binding properties causing severe…
This paper proposes a distributed attack detection and mitigation technique based on distributed estimation over a multi-agent network, where the agents take partial system measurements susceptible to (possible) biasing attacks. In…
We propose an efficient multiband absorber comprising a truncated one-dimensional periodic metal-dielectric photonic crystal and a reflective substrate. The reflective substrate is actually an optically thick metallic film. Such a planar…
Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, which denotes that the…