CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
CoopGuard:基于协作代理的有状态多轮防御框架用于抵御LLM的演变攻击
Siyuan Li, Zehao Liu, Xi Lin, Qinghua Mao, Yuliang Chen, Haoyu Li, Jun Wu, Jianhua Li, Xiu Su
机构
*
School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学与工程学院)
;
Department of Computer Science, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校计算机科学系)
;
Big Data Institute, Central South University(中南大学大数据研究院)
CommentsThis article is adapted from Perplexity's response to NIST/CAISI Request for Information 2025-0035. 91 Fed. Reg. 698 (Jan. 8, 2026). The originally submitted response can be found on the public docket at https://www.regulations.gov/comment/NIST-2025-0035-0505
机构
*
Arizona State University(亚利桑那州立大学)
;
Morgan Stanley(摩根士丹利)
;
UC Davis(加州大学戴维斯分校)
;
Washington University in St. Louis(圣路易斯华盛顿大学)
;
Rice University(莱斯大学)
;
Florida State University(佛罗里达州立大学)
;
University of Oxford(牛津大学)
Comments26 pages, 6 figures, 7 tables; identifies a vulnerability in the heartbeat mechanism of Claw systems with version-scoped evaluation (pre-fix OpenClaw, February 2026)
Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization
子空间控制:将受约束的模型操控转化为可控的谱优化
Yancheng Huang, Changsheng Wang, Chongyu Fan, Yicheng Lang, Bingqi Shang, Yang Zhang, Mingyi Hong, Qing Qu, Alvaro Velasquez, Sijia Liu
机构
*
OPTML, Michigan State University(OPTML,密歇根州立大学)
;
MIT-IBM Watson AI Lab, IBM Research(MIT-IBM Watson AI Lab,IBM研究院)
;
University of Minnesota(明尼苏达大学)
;
University of Michigan(密歇根大学)
;
University of Colorado Boulder(科罗拉多大学博尔德分校)
ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMs
ALIEN:对齐熵头以提高大语言模型的不确定性估计
Artem Zabolotnyi, Roman Makarov, Mile Mitrovic, Polina Proskura, Oleg Travkin, Roman Alferov, Alexey Zaytsev
机构
*
Applied AI Institute, Moscow, Russia(应用人工智能研究所,莫斯科,俄罗斯)
;
SB AI Lab, Moscow, Russia(SB AI实验室,莫斯科,俄罗斯)
;
Intellectual data analysis and predictive modeling Institute, Moscow, Russia(智能数据分析与预测建模研究所,莫斯科,俄罗斯)
Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapters
通过正交化低秩适配器实现大规模语言模型的可扩展变分贝叶斯微调
Haotian Xiang, Bingcong Li, Qin Lu
机构
*
School of Electrical and Computer Engineering, University of Georgia(佐治亚大学电气与计算机工程学院)
;
Department of Computer Science, ETH Zurich(苏黎世联邦理工学院计算机科学系)
Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
超越全局评分:细粒度令牌接地作为检测LVLM幻觉的稳健检测器
Tuan Dung Nguyen, Minh Khoi Ho, Qi Chen, Yutong Xie, Nguyen Cam-Tu, Minh Khoi Nguyen, Dang Huy Pham Nguyen, Anton van den Hengel, Johan W. Verjans, Phi Le Nguyen, Vu Minh Hieu Phan
机构
*
Hanoi University of Science and Technology(河内科技大学)
;
Australian Institute for Machine Learning, University of Adelaide(澳大利亚机器学习研究所,阿德莱德大学)
;
Nanjing University(南京大学)
;
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
;
Hanoi-Amsterdam High School for the Gifted(河内阿姆斯特丹天才高中)
Quantifying Trust: Financial Risk Management for Trustworthy AI Agents
量化信任:为可信AI代理的金融风险管理
Wenyue Hua, Tianyi Peng, Chi Wang, Ian Kaufman, Bryan Lim, Chandler Fang
机构
*
Microsoft Research(微软研究院)
;
Columbia University(哥伦比亚大学)
;
Google DeepMind(谷歌DeepMind)
;
Stanford University(斯坦福大学)
;
t54.ai
;
Virtuals ACP
;
University of California, Santa Barbara(加州大学圣塔芭芭拉分校)