paper-with-me

Papers

Shielded Analysis: Certification and Characterization of Defensibility in Systems under Adversarial Interaction

2026-06-11 · Achraf Hsain, Sultan Almuhammadi arxiv

Formal safety analysis determines whether a system admits a safe defense; adaptive evaluation characterizes the operating quality sustained under adversarial interaction. Both answers matter because systems with the same safety verdict can impose very different operational burdens. We introduce shielded analysis, a design-time framework that derives these answers from one encoded system while keeping the safety requirement and admissible threat model independently variable. It returns a defensibility certificate and a four-axis defensibility fingerprint spanning structural margin, shield latitude, and adaptive operating quality. Each axis is informative in its own right; their relationships show whether formal and operational assessments agree, diverge, or respond differently to system changes. We instantiate the framework for network defense on a reference segment and four controlled perturbations spanning topology, safety requirements, and adversary capabilities. Every configuration is certified defensible, yet two topology variants with nearly identical structural profiles sustain mean clean-host fractions of 22.7% and 80.7% under adaptive pressure. Shielded analysis turns a safety-game solution into a comparative instrument: it determines whether a defense exists, characterizes what that defense requires, and identifies which system changes strengthen it.

📄 PDF Abstract BibTeX arXiv:2606.13621

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Probabilistic Stability Guarantees for Feature Attributions

2025-04-18 · Helen Jin, Anton Xue, Weiqiu You, Surbhi Goel 외

Stability guarantees have emerged as a principled way to evaluate feature attributions, but existing certification methods rely on heavily smoothed classifiers and often produce conservative guarantees. To address these …

Escaping the Agreement Trap: Defensibility Signals for Evaluating Rule-Governed AI

2026-04-22 · Michael O'Herlihy, Rosa Català arxiv

Content moderation systems are typically evaluated by measuring agreement with human labels. In rule-governed environments this assumption fails: multiple decisions may be logically consistent with the governing policy, …

Shielded RecRL: Explanation Generation for Recommender Systems without Ranking Degradation

2025-10-14 · Ansh Tiwari, Ayush Chauhan arxiv

We introduce Shielded RecRL, a reinforcement learning approach to generate personalized explanations for recommender systems without sacrificing the system's original ranking performance. Unlike prior RLHF-based recommen…

Reinforcement LearningExplanation Generation

Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learning

2024-11-07 · Satchit Chatterji, Erman Acar

Safe reinforcement learning (RL) is crucial for real-world applications, and multi-agent interactions introduce additional safety challenges. While Probabilistic Logic Shields (PLS) has been a powerful proposal to enforc…

Multi-agent Reinforcement LearningQ-Learningreinforcement-learningReinforcement Learning+2

Artificial intelligence for representing and characterizing quantum systems

2025-09-05 · Yuxuan Du, Yan Zhu, Yuan-Hang Zhang, Min-Hsiu Hsieh 외 arxiv

Efficient characterization of large-scale quantum systems, especially those produced by quantum analog simulators and megaquop quantum computers, poses a central challenge in quantum science due to the exponential scalin…