The paper proposes evaluating certified training methods by comparing their Pareto fronts across the natural-certified accuracy trade-off, revealing superior performance and previously unappreciated c…

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 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 introduces SORA, an adaptive adversarial training method that dynamically adjusts perturbation sizes to prevent Catastrophic Overfitting, achieving state-of-the-art robustness and clean accu…

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…

The paper introduces EnsembleSHAP, a novel, computationally efficient, and provably robust feature attribution method specifically designed for the Random Subspace Method to provide secure explanation…

This study longitudinally evaluates the adversarial robustness of Android malware detection systems over a decade, finding that temporal separation significantly degrades robustness due to concept dri…

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 establishes a standardized security assessment framework and develops a multi-layered defensive system, demonstrating that systematic testing and external defenses are crucial for safe LLM d…

The paper introduces a sample-wise targeted adversarial attack that successfully misclassifies only specific, triggered inputs during test-time adaptation while maintaining the overall label distribut…

The paper introduces ParDef, a generalized defense mechanism that effectively mitigates various types of parameter attacks on deep neural networks while maintaining high performance.

The paper formally proves a theorem regarding adversarial noise amplification and proposes a novel, lightweight detection mechanism that uses this enhanced signal for robust adversarial defense.

The paper demonstrates that fine-tuning safety guard models on benign data can catastrophically collapse their safety alignment, proposing Fisher-Weighted Safety Subspace Regularization (FW-SSR) to ac…

The paper proposes a certifiably robust malware detection framework using randomized smoothing and feature ablation to guarantee detection accuracy against metamorphic evasion attacks.

This paper demonstrates that neural operators used in digital twins for nuclear systems are highly vulnerable to undetectable, sparse adversarial perturbations, necessitating new robustness guarantees…

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…

GuardNet is a lightweight, ensemble-based guardrail system using shallow neural networks that provides robust and efficient detection of Prompt Injection and Jailbreak attacks on LLMs, suitable for pr…

The paper proposes a universal robustification framework to enhance drift-adaptive malware detectors against combined concept drift and adversarial attacks, significantly reducing attack success rates…

This paper analyzes how vulnerable various machine learning models are to data poisoning attacks in IoT intrusion detection, finding that ensemble methods are more robust than Logistic Regression and…

This paper enhances the adversarial robustness of a CNN used for time-series classification in crystal-collimator alignment by developing a differentiable wrapper and employing adversarial fine-tuning…