Related papers: AdaTest:Reinforcement Learning and Adaptive Sampli…
The 3D Lookup Table (3D LUT) is a highly-efficient tool for real-time image enhancement tasks, which models a non-linear 3D color transform by sparsely sampling it into a discretized 3D lattice. Previous works have made efforts to learn…
Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolving task distributions. Existing approaches rely on fixed compression strategies (e.g.,…
The integration of AI into modern critical infrastructure systems, such as healthcare, has introduced new vulnerabilities that can significantly impact workflow, efficiency, and safety. Additionally, the increased connectivity has made…
Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained. To overcome this limitation, new gradient…
Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor…
Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks. This impedes their wider adoption, especially in mission critical applications. This paper tackles the problem of Trojan…
LLM alignment remains a critical challenge. Inference-time methods provide a flexible alternative to fine-tuning, but their uniform computational effort often yields suboptimal alignment. We hypothesize that for many alignment tasks, the…
This paper presents a novel adaptation of the Stochastic Gradient Descent (SGD), termed AdaBatchGrad. This modification seamlessly integrates an adaptive step size with an adjustable batch size. An increase in batch size and a decrease in…
Predicting and classifying faults in electricity networks is crucial for uninterrupted provision and keeping maintenance costs at a minimum. Thanks to the advancements in the field provided by the smart grid, several data-driven approaches…
Test-Time Adaptation (TTA) offers a practical solution for deploying image segmentation models under domain shift without accessing source data or retraining. Among existing TTA strategies, pseudo-label-based methods have shown promising…
The increased usage of Internet of Things devices at the network edge and the proliferation of microservice-based applications create new orchestration challenges in Edge computing. These include detecting overutilized resources and scaling…
Trojan backdoor is a poisoning attack against Neural Network (NN) classifiers in which adversaries try to exploit the (highly desirable) model reuse property to implant Trojans into model parameters for backdoor breaches through a poisoned…
Adversarial examples present significant challenges to the security of Deep Neural Network (DNN) applications. Specifically, there are patch-based and texture-based attacks that are usually used to craft physical-world adversarial examples,…
Deep neural networks have demonstrated remarkable success across numerous tasks, yet they remain vulnerable to Trojan (backdoor) attacks, raising serious concerns about their safety in real-world mission-critical applications. A common…
Adversarial training has become the primary method to defend against adversarial samples. However, it is hard to practically apply due to many shortcomings. One of the shortcomings of adversarial training is that it will reduce the…
Deep learning algorithms have become an essential component in the field of cognitive radio, especially playing a pivotal role in automatic modulation classification. However, Deep learning also present risks and vulnerabilities. Despite…
We study an adaptive source seeking problem, in which a mobile robot must identify the strongest emitter(s) of a signal in an environment with background emissions. Background signals may be highly heterogeneous and can mislead algorithms…
Prompt Tuning (PT) enables the adaptation of Pre-trained Large Language Models (PLMs) to downstream tasks by optimizing a small amount of soft virtual tokens, which are prepended to the input token embeddings. Recently, Decomposed Prompt…
Backdoors pose a serious threat to machine learning, as they can compromise the integrity of security-critical systems, such as self-driving cars. While different defenses have been proposed to address this threat, they all rely on the…
Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false…