This paper proposes using random sampling of prediction precision during inference to significantly enhance the adversarial robustness of Automatic Speech Recognition (ASR) systems.

The paper proposes a unified, architecture-agnostic framework that significantly improves the robustness of deepfake image detectors against adversarial attacks by focusing on higher-order frequency s…

The paper demonstrates that simpler, shallower Deep Neural Network architectures with reduced features and ReLU activations can inherently improve the robustness of ML-NIDS against gradient-based adve…

This survey provides a detailed overview of quantum adversarial machine learning, examining existing attacks, novel quantum-enhanced defense strategies, and the theoretical challenges in securing quan…

The paper proposes a Distribution-aware Dynamic Guidance (DDG) strategy to mitigate catastrophic overfitting and the robustness-accuracy trade-off inherent in Fast Adversarial Training (FAT) by dynami…

The paper proposes CEAR, an ensemble-based method that combines empirical and certified defenses to achieve superior provable robustness against adversarial attacks in Deep Neural Networks.

The paper proposes LARAR, a novel layer-wise adaptive regularization approach that enhances the adversarial robustness of neural network-based Network Intrusion Detection Systems by analyzing and miti…

The paper reviews adversarial machine learning vulnerabilities and proposes conceptual frameworks for enhancing AI robustness by integrating quantum computing techniques.

The paper reviews the vulnerability of AI to adversarial attacks and proposes conceptual frameworks for enhancing AI robustness by integrating quantum computing techniques.

The paper introduces 'adversarial restlessness,' an activation-level signature in LLM residual streams, to detect multi-turn prompt injection attacks with high accuracy.

The paper demonstrates that current AI watermark removal techniques fail to achieve true forensic stealth, as the removal process often leaves behind detectable signals that distinguish the output fro…

The paper introduces Dummy-Aware Weighted Attack (DAWA), a novel evaluation method that significantly reduces the reported robustness of Dummy Classes-based defenses by simultaneously targeting both t…

The paper proposes combining Gaussian noise and bilateral filtering into a simple preprocessor that achieves supralinear and scalable adversarial robustness in CNNs with significantly reduced computat…

The paper introduces a novel Clean-Referenced Feature-Vocoder Attack, a black-box adversarial attack that perturbs high-level SSL feature representations instead of raw audio waveforms, achieving supe…

NeuroTrace introduces a novel framework using Inference Provenance Graphs (IPGs) to analyze the information flow during deep neural network inference, demonstrating that this provenance provides a rob…

The paper proposes a novel method to generate adversarial malware samples that evade deep learning detectors while simultaneously minimizing the detectable 'drift' signals, showing that similarity con…

The paper proposes RESSAP, a novel ensemble framework that significantly enhances the robustness of machine learning classifiers against adversarial evasion attacks by combining feature selection, ens…

The paper proposes a novel structural invariant approach, derived from the economic constraints of fraud, that amplifies weak, low-precision signals into highly accurate fraud detections without requi…

This paper evaluates a novel black-box adversarial attack to demonstrate the vulnerability of ML-based IoT Intrusion Detection Systems (IDS) and proposes a robust defense mechanism to mitigate these e…

The paper demonstrates that current defenses against malicious fine-tuning of foundation models are insufficient because they only address fixed attacks, and introduces a unified adaptive attack that…