This paper shows that under standard assumptions, there is no polynomial-time verifier for exact verification of ReLU networks in an adversarial smoothed model.

The paper proposes a novel framework using the primal-dual perspective of differential privacy to provide a unified, modular, and end-to-end robustness certification for complex machine learning model…

The paper introduces Disrupt-and-Rectify Smoothing (DR-Smoothing), a novel two-stage defense mechanism that significantly improves LLM security against jailbreaking attacks by restoring disrupted inpu…

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 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 introduces Singularity-aware Adam (S-Adam), a novel optimizer that stabilizes deep learning training in non-smooth loss landscapes by dynamically damping updates based on local geometric ins…

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

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…

This paper provides the first non-vacuous generalization analysis for the Stochastic Variance Reduced Gradient (SVRG) method by establishing sharp, data-dependent algorithmic stability bounds, thereby…

This paper proves the conjecture that Local SGD outperforms Mini-batch SGD under bounded second-order heterogeneity for general convex objectives, improving the convergence guarantee and lower bounds.

The paper proposes AEGIS, a novel diffusion-guided method for injecting adversarial perturbations into the latent space to create generalizable and robust defenses against advanced facial deepfake man…

This paper proposes a novel estimator for the target linear coefficient in a partial linear model with black-box nuisance estimation and establishes its unimprovable error rate.

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 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 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 proposes WARDEN, a distributionally robust adversarial training framework that significantly reduces LLM vulnerability to adversarial attacks by dynamically reweighting hard adversarial exam…

The paper introduces AdvScene, a novel scene-grounded framework that measures the real-world 'scene robustness' of adversarial patches by characterizing their operational envelope across varying viewp…

The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensiti…

The paper introduces GPIC, a massive, permissively licensed, and safety-filtered image corpus of 28 trillion pixels, designed to serve as a stable and accessible benchmark for large-scale visual gener…