Related papers: Aura-CAPTCHA: A Reinforcement Learning and GAN-Enh…

A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack…

The security of Deep Reinforcement Learning (Deep RL) algorithms deployed in real life applications are of a primary concern. In particular, the robustness of RL agents in cyber-physical systems against adversarial attacks are especially…

Deep learning has emerged as a leading approach for Automatic Modulation Classification (AMC), demonstrating superior performance over traditional methods. However, vulnerability to adversarial attacks and susceptibility to data…

We propose a novel technique to make neural network robust to adversarial examples using a generative adversarial network. We alternately train both classifier and generator networks. The generator network generates an adversarial…

The synergies between Quality-Diversity (QD) and Deep Reinforcement Learning (RL) have led to powerful hybrid QD-RL algorithms that have shown tremendous potential, and brings the best of both fields. However, only a single deep RL…

Long-horizon navigation in complex urban environments relies heavily on continuous human operation, which leads to fatigue, reduced efficiency, and safety concerns. Shared autonomy, where a Vision-Language AI agent and a human operator…

In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can…

The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…

Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar…

An important issue with Large Language Models (LLMs) is their undesired ability to generate toxic language. In this work, we show that the neurons responsible for toxicity can be determined by their power to discriminate toxic sentences,…

This study developed a generative adversarial network (GAN)-based defense method for traffic sign classification in an autonomous vehicle (AV), referred to as the attack-resilient GAN (AR-GAN). The novelty of the AR-GAN lies in (i) assuming…

The performance of facial super-resolution methods relies on their ability to recover facial structures and salient features effectively. Even though the convolutional neural network and generative adversarial network-based methods deliver…

In question-answering (QA) systems, Retrieval-Augmented Generation (RAG) has become pivotal in enhancing response accuracy and reducing hallucination issues. The architecture of RAG systems varies significantly, encompassing single-round…

Completely Automated Public Turing test to tell Computers and Humans Apart, short for CAPTCHA, is an essential and relatively easy way to defend against malicious attacks implemented by bots. The security and usability trade-off limits the…

Model fusion is a key strategy for robust recognition in unconstrained scenarios, as different models provide complementary strengths. This is especially important for whole-body human recognition, where biometric cues such as face, gait,…

The rapid proliferation of AI-Generated Images (AIGIs) has introduced severe risks of misinformation, making AIGI detection a critical yet challenging task. While traditional detection paradigms mainly rely on low-level features, recent…

Pre-trained models for automatic speech recognition (ASR) and speech enhancement (SE) have exhibited remarkable capabilities under matched noise and channel conditions. However, these models often suffer from severe performance degradation…

Recent advances in reinforcement learning (RL) and Human-in-the-Loop (HitL) learning have made human-AI collaboration easier for humans to team with AI agents. Leveraging human expertise and experience with AI in intelligent systems can be…

Downstream fine-tuning of vision-language-action (VLA) models enhances robotics, yet exposes the pipeline to backdoor risks. Attackers can pretrain VLAs on poisoned data to implant backdoors that remain stealthy but can trigger harmful…

Generative Adversarial Networks (GAN) have emerged as a formidable AI tool to generate realistic outputs based on training datasets. However, the challenge of exerting control over the generation process of GANs remains a significant…