Related papers: Multivalent "Attacker & Guard" Strategy for Target…
In this paper, we propose a multi-generator extension to the adversarial training framework, in which the objective of each generator is to represent a unique component of a target mixture distribution. In the training phase, the generators…
Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…
This study proposes a distributed algorithm that makes agents' adaptive grouping entrap multiple targets via automatic decision making, smooth flocking, and well-distributed entrapping. Agents make their own decisions about which targets to…
We present the algorithm for generating strictly saturated random sequential adsorption packings built of rounded polygons. It can be used to study various properties of such packings built of a wide variety of different shapes and in…
We exploit multi-path fading propagation to improve both the signal-to-interference-plus-noise-ratio and the stability of wireless communications within electromagnetic environments that support rich multipath propagation. Quasi-passive…
Adversarial attack patches have gained increasing attention due to their practical applicability in physical-world scenarios. However, the bright colors used in attack patches represent a significant drawback, as they can be easily…
Multi-component self-assembly mixtures offer the possibility of encoding multiple target structures with the same set of interacting components. Selective retrieval of one of the stored structures has been attempted by preparing an initial…
The Walker-Anderson half-space penetration model has been successfully used for the rapid, efficient calculation of penetration of walls by rigid and eroding rods. These models align well with detailed simulations for thick targets;…
LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are optimized for efficiency rather than safety, can be manipulated by adversarial inputs,…
Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…
Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-decoder, and decoder-only models. However, unlike CLIP…
Molecular communication is a promising solution to enable intra-body communications among nanomachines. However, malicious and non-cooperative receivers can degrade the performance, compromising these systems' security. Analyzing the…
Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrated to be one of the most successful adversarial attacks.…
Theoretical studies of self-assembly processes and condensed phases in colloidal systems are often based on effective inter-particle potentials. Here we show that developing an effective potential for particles interacting with a limited…
This paper presents a novel coverage control algorithm for multi-agent systems, where each agent has no prior knowledge of the specific region to be covered. The proposed method enables agents to autonomously detect the target area and…
A mathematical model is presented for predicting magnetic targeting of multifunctional carrier particles that are designed to deliver therapeutic agents to malignant tissue in vivo. These particles consist of a nonmagnetic core material…
In distributed learning agents aim at collaboratively solving a global learning problem. It becomes more and more likely that individual agents are malicious or faulty with an increasing size of the network. This leads to a degeneration or…
A new mechanism of enhanced laser energy absorption in plasma microglobules is demonstrated with the help of two-dimensional Particle-In-Cell (PIC) simulations. The mechanism relies on the excitation of surface and bulk waves and the…
As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and…
We consider a wireless communication system, where a transmitter sends signals to a receiver with different modulation types while the receiver classifies the modulation types of the received signals using its deep learning-based…