paper-with-me

홈 › Papers

Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization

2026-03-04 · Furkan Mumcu, Yasin Yilmaz arxiv

As Large Language Models (LLMs) transition into autonomous multi-agent ecosystems, robust minimax training becomes essential yet remains prone to instability when highly non-linear policies induce extreme local curvature in the inner maximization. Standard remedies that enforce global Jacobian bounds are overly conservative, suppressing sensitivity in all directions and inducing a large Price of Robustness. We introduce Adversarially-Aligned Jacobian Regularization (AAJR), a trajectory-aligned approach that controls sensitivity strictly along adversarial ascent directions. We prove that AAJR yields a strictly larger admissible policy class than global constraints under mild conditions, implying a weakly smaller approximation gap and reduced nominal performance degradation. Furthermore, we derive step-size conditions under which AAJR controls effective smoothness along optimization trajectories and ensures inner-loop stability. These results provide a structural theory for agentic robustness that decouples minimax stability from global expressivity restrictions.

📄 PDF Abstract BibTeX arXiv:2603.04378

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Jacobian Adversarially Regularized Networks for Robustness

2019-12-21 · ICLR 2020 1 · Alvin Chan, Yi Tay, Yew Soon Ong, Jie Fu

Adversarial examples are crafted with imperceptible perturbations with the intent to fool neural networks. Against such attacks, adversarial training and its variants stand as the strongest defense to date. Previous stud…

Adversarially robust generalization theory via Jacobian regularization for deep neural networks

2024-12-17 · Dongya Wu, Xin Li

Powerful deep neural networks are vulnerable to adversarial attacks. To obtain adversarially robust models, researchers have separately developed adversarial training and Jacobian regularization techniques. There are abu…

Adversarial Attack

Benchmarking the Robustness of Agentic Systems to Adversarially-Induced Harms

2025-08-22 · Jonathan Nöther, Adish Singla, Goran Radanovic arxiv

Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic s…

Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense

2022-07-09 · Deyin Liu, Lin Wu, Haifeng Zhao, Farid Boussaid 외

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples that are crafted with imperceptible perturbations, i.e., a small change in an input image can induce a mis-classification, and thus threatens…

Adversarial Defense

Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety

2026-06-26 · Ting Ma, Xiufeng Huang, Benlei Cui, Xiaowen Xu 외 arxiv

As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safety is adversarial: many failures arise no…

Adversarial RobustnessReinforcement Learning