This paper systematically studies the robustness of vision foundation models to common image perturbations, finding that most models are generally non-robust and proposing a fine-tuning method to impr…

The paper proposes a novel zeroth-order optimization framework to enhance the robustness of LLM safety alignment, showing that few refinement steps can significantly improve safety while maintaining u…

The paper proposes a debiasing fine-tuning technique to efficiently enhance the robustness of Large Language Models against semantically similar but textually altered prompts.

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…

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 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 proposes W-IR, a novel watermarking framework that simultaneously achieves high certified robustness against adversarial attacks and effectively mitigates identity leakage in watermarked ima…

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 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 Auto-ART, a comprehensive open-source framework that provides structured meta-analysis and automated testing for adversarial robustness, revealing significant gaps in current ML s…

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…

The paper establishes a theoretical information-theoretic bound proving that for Vision-Language-Action (VLA) models, capability and robustness cannot both be arbitrarily high, quantifying the trade-o…

The paper analyzes robust covert wireless communication under bounded uncertainty, demonstrating that the adverse conditions governing reliability and covertness are distinct, thus requiring a conflic…

This paper studies adversarial attacks on programming-by-example systems and introduces a defense method called version-space partition aggregation (VPA).

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.

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

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 argues that current 'on-the-fly' AI agent design lacks necessary software engineering rigor and proposes an 'AI Workflow Store' to provide hardened, reusable, and reliable agent workflows.