大模型对齐与安全 - arXivDaily 专题

2102.08111 2021-11-30 stat.AP cs.LG cs.SY eess.SY 57%

Multivariable Fractional Polynomials for lithium-ion batteries degradation models under dynamic conditions

Clara Bertinelli Salucci, Azzeddine Bakdi, Ingrid K. Glad, Erik Vanem, Riccardo De Bin

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Comments 45 pages, 7 figures, 3 tables

2106.05825 2021-09-29 cs.CR cs.AR cs.LG 57%

HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks

Mohammad Hossein Samavatian, Saikat Majumdar, Kristin Barber, Radu Teodorescu

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Journal ref Secure and Private Systems for Machine Learning Workshop 2021

2108.04990 2021-09-16 cs.CL 57%

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing

Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon, Yangfeng Ji, Yanjun Qi

专题命中越狱攻击：trustworthy(abstract)；分类 cs.CL

Comments EMNLP-BlackboxNLP, 2021

2010.01746 2021-08-10 cs.LG 57%

Data-driven Operation of the Resilient Electric Grid: A Case of COVID-19

Hossein Noorazar, Anurag. k. Srivastava, K. Sadanandan Sajan, Sanjeev Pannala

专题命中越狱攻击：safety(abstract)；分类 cs.LG

2107.14100 2021-07-30 cs.CY 57%

Smart Band: An Integrated Device for Emergency Management

A. Jackulin Mahariba, Shivam Patel

专题命中越狱攻击：safety(abstract)；分类 cs.CY

Comments 3 pages, 6 figures

Journal ref International Journal of Engineering and Advanced Technology, Volume-8 Issue-4S2, April 2019

2103.07110 2021-03-15 cs.CR cs.AI 57%

Explaining Network Intrusion Detection System Using Explainable AI Framework

Shraddha Mane, Dattaraj Rao

专题命中越狱攻击：safety(abstract)；分类 cs.AI

1812.02132 2020-11-30 cs.CV cs.CR cs.LG cs.RO 57%

SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications

Abdullah Hamdi, Matthias Müller, Bernard Ghanem

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Comments Accepted at AAAI'20

Journal ref AAAI 2020

2011.00540 2020-11-03 cs.CR cs.LG 57%

Unsupervised Intrusion Detection System for Unmanned Aerial Vehicle with Less Labeling Effort

Kyung Ho Park, Eunji Park, Huy Kang Kim

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Comments 14 pages, 4 tables, 3 figures, 5 equations, In Proceeding of WISA 2020 (THE 21ST WORLD CONFERENCE ON INFORMATION SECURITY APPLICATIONS)

2005.14137 2020-05-29 cs.LG cs.CV stat.ML 57%

QEBA: Query-Efficient Boundary-Based Blackbox Attack

Huichen Li, Xiaojun Xu, Xiaolu Zhang, Shuang Yang, Bo Li

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Comments Accepted by CVPR 2020

1909.08072 2019-10-10 cs.LG cs.CR stat.ML 57%

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Han Xu, Yao Ma, Haochen Liu, Debayan Deb, Hui Liu, Jiliang Tang, Anil K. Jain

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Comments survey, adversarial attacks, defenses

1907.11129 2019-07-26 cs.LG cs.CR cs.NE stat.AP stat.ML 57%

Semisupervised Adversarial Neural Networks for Cyber Security Transfer Learning

Casey Kneale, Kolia Sadeghi

专题命中越狱攻击：alignment(abstract)；分类 cs.LG

Comments 14 figures, 17 pages, Draft

1906.07077 2019-06-18 cs.LG cs.CR stat.ML 57%

The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks

Felix Assion, Peter Schlicht, Florens Greßner, Wiebke Günther, Fabian Hüger, Nico Schmidt, Umair Rasheed

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Comments CVPR SAIAD - Workshop 2019

1804.05810 2019-05-02 cs.CV cs.CR cs.LG stat.ML 57%

ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector

Shang-Tse Chen, Cory Cornelius, Jason Martin, Duen Horng Chau

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Journal ref Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 52-68, 2018

1812.02575 2018-12-08 stat.ML cs.CR cs.LG 57%

Prior Networks for Detection of Adversarial Attacks

Andrey Malinin, Mark Gales

专题命中越狱攻击：safety(abstract)；分类 cs.LG

1709.03423 2018-02-09 stat.ML cs.LG 57%

Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networks

Thilo Strauss, Markus Hanselmann, Andrej Junginger, Holger Ulmer

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Comments 10 pages, 2 figures, 4 tables

1711.05934 2017-11-17 cs.CV cs.CR cs.LG 57%

Enhanced Attacks on Defensively Distilled Deep Neural Networks

Yujia Liu, Weiming Zhang, Shaohua Li, Nenghai Yu

专题命中越狱攻击：safety(abstract)；分类 cs.LG

1710.00814 2017-10-04 cs.CV cs.CR cs.LG 57%

Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight

Yen-Chen Lin, Ming-Yu Liu, Min Sun, Jia-Bin Huang

专题命中越狱攻击：safety(abstract)；分类 cs.LG

Comments Project page: http://yclin.me/RL_attack_detection/ Code: https://github.com/yenchenlin/rl-attack-detection

2407.01606 2024-07-03 cs.LG cs.AI cs.CL cs.CV stat.ML 56%

On Discrete Prompt Optimization for Diffusion Models

Ruochen Wang, Ting Liu, Cho-Jui Hsieh, Boqing Gong

专题命中越狱攻击：分类 cs.CL、cs.AI、cs.LG；DPO(comments)

Comments ICML 2024. Code available at https://github.com/ruocwang/dpo-diffusion

Journal ref Proceedings of the 41st International Conference on Machine Learning (ICML 2024)

2601.05150 2026-08-25 cs.CR 版本更新 50%

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models

$PC^2$：通过基于GPT的文本到图像模型的越狱攻击生成政治争议内容

Wonwoo Choi, Minjae Seo, Minkyoo Song, Hwanjo Heo, Seungwon Shin, Myoungsung You

专题命中越狱攻击：safety(abstract)

AI总结提出首个黑盒政治越狱框架$PC^2$，利用身份保留描述映射和地缘政治远距离翻译绕过安全过滤器，在GPT系列模型上实现高达86%的攻击成功率。

Comments To appear in the 33rd ACM Conference on Computer and Communications Security (CCS 2026)

2608.20748 2026-08-24 cs.CV 新提交 50%

Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer

为视觉几何接地Transformer生成多视角对抗样本

Qi Song, Ziyuan Luo, Haoliang Han, Renjie Wan

机构 * Hong Kong Baptist University（香港浸会大学）

专题命中越狱攻击：alignment(abstract)

AI总结本研究针对3D基础模型VGGT的安全漏洞，提出MVAP-G多视角对抗扰动生成器，通过跨视角对抗对齐机制生成一致扰动，可无需迭代优化即可显著降低VGGT性能，为3D视觉系统鲁棒性研究提供了新方向。

Comments ECCV 2026

2608.19135 2026-08-20 cs.CR cs.DC cs.MA cs.NI 新提交 50%

Autonomous Cyber Defense in Connected Vehicles: A Multi-Agent Approach to V2X Security

网联车辆中的自主网络防御：一种面向V2X安全的多智能体方法

Krishna Teja Medam

专题命中越狱攻击：safety(abstract)

AI总结针对网联车辆V2X安全，提出三层多智能体架构，以SAE标准时序为硬性约束，分层处理消息分类、冲突解决与模型优化，解决现有入侵检测系统的安全-安保冲突问题。

2608.13671 2026-08-17 cs.CV 新提交 50%

PROVE: Training-Free Prompt Recovery using Verifiable Evidence

PROVE：基于可验证证据的无训练提示词恢复

Rupayan Mallick, Mahsa Khoshnoodi, Sarah Adel Bargal

专题命中越狱攻击：alignment(abstract)

AI总结该研究提出无训练的黑盒提示词反转攻击PROVE，通过可验证场景描述重建提示词，在多数据集上优于基线方法，可用于版权保护相关研究。

2603.22928 2026-08-12 cs.CR 版本更新 50%

SoK: The Attack Surface of Agentic AI - Tools and Autonomy

SoK：代理AI的攻击面——工具与自主性

Ali Dehghantanha, Sajad Homayoun

专题命中越狱攻击：prompt injection(abstract)

AI总结本文系统分析了代理AI的安全风险，提出攻击分类与评估指标，探讨防御措施及开放研究挑战，帮助研究人员和工程师应对代理AI的安全威胁。

2603.04469 2026-08-06 cs.CR cs.MA 版本更新 50%

Cross-Layer Semantic Flow Reconstruction for Attack Detection in Agentic Systems

超越输入防护：为执行感知攻击检测重建跨代理语义流

Qizhi Cai, Yangyang Wei, Zhipeng Chen, Shouling Ji, Zhenyuan Li

专题命中越狱攻击：prompt injection(abstract)

AI总结 SysName通过重建跨代理语义流，实现执行感知的攻击检测，有效识别多种复合攻击向量，提升多代理系统安全性。

Comments 16 pages, 15 figures

2509.20851 2026-08-05 cs.CV 版本更新 50%

Poisoning Prompt-Guided Sampling in Video Large Language Models

针对视频大语言模型中提示引导采样的投毒攻击

Yuxin Cao, Wei Song, Jingling Xue, Jin Song Dong

机构 * National University of Singapore（新加坡国立大学）； University of New South Wales（新南威尔士大学）； CSIRO’s Data61（CSIRO数据61）

专题命中越狱攻击：safety(abstract)

AI总结该研究针对视频大语言模型的提示引导采样提出PoisonVID投毒攻击，在多种模型与采样器组合上实现高攻击成功率，揭示了PGS存在的结构性安全隐患。

Comments 16 pages, 5 figures

2608.01117 2026-08-04 cs.CR 新提交 50%

SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks

SoK：面向意图的多轮大语言模型越狱系统化研究

Siyuan Li, Aodu Wulianghai, Zehao Liu, Xi Lin, Qinghua Mao, Haoyu Li, Xiang Chen, Siyuan Liang, Jun Wu, Jianhua Li, Dacheng Tao

专题命中越狱攻击：safety(abstract)

AI总结本研究提出面向意图的多轮LLM越狱分类法，发现攻击有效性取决于意图组织精细度，推动检测范围升级，表明轮级安全机制不足，需对应层级评估协议。

2607.25936 2026-07-29 cs.CR 新提交 50%

From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs

从角色提示到无限思考：利用角色条件进行大语言模型推理成本攻击

Zhiyi Mou, Wangze Ni, Tianfang Xiao, Haoyang LI, Chen Jason Zhang, Hanzhi Ma, Yang Bai, Zhibo Wang, Kui Ren

专题命中越狱攻击：alignment(abstract)

AI总结研究LLMs推理成本问题，提出RolePlay框架利用角色条件诱导低效行为放大推理成本，实验证明该框架优于现有方法，为LLM推理效率攻击提供新视角。

Comments 17pages

2607.21243 2026-07-24 cs.CV 新提交 50%

Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks

检测器学习到错误的东西：针对物理可实现攻击的抗捷径对抗训练

Yuanhao Huang, Yilong Ren, Jinlei Wang, Xuesong Bai, Zheng Zhang, Haiyang Yu

机构 * School of Transportation Science and Engineering, Beihang University（北京航空航天大学交通科学与工程学院）； State Key Lab of Intelligent Transportation System（智能交通系统国家重点实验室）； Zhongguancun Laboratory（中关村实验室）； School of Systems Science and Engineering, Sun Yat-Sen University（中山大学系统科学与工程学院）； Shandong Sino-Aisa Tire Proving Ground Co.,Ltd.（山东中亚洲轮胎试验场有限公司）

专题命中越狱攻击：safety(abstract)

AI总结研究针对物理可实现攻击，提出实例级对比对抗训练框架InsCAT，通过SICA、ROPO和Guard等方法防止检测器将对抗纹理用作独立决策线索，经实验验证其在多场景和检测器上效果良好，提升检测可靠性。

2607.19545 2026-07-23 cs.CR 新提交 50%

When HTTP 402 Meets the Blockchain: Risks on Emerging x402 Payments

当HTTP 402遇上区块链：新兴x402支付的风险

Qinying Wang, Yong Yang, Yuan Chen, Shouling Ji, Mathias Payer

专题命中越狱攻击：safety(abstract)

AI总结研究x402支付协议，通过系统研究确定促进者的安全规则，基于规则违规分析得出新攻击向量，提出半自动黑盒工具评估安全性，发现部署均有违规，还通过实证测量量化相关指标，揭示其安全风险。

Journal ref USENIX Security 2026

2602.06409 2026-07-22 cs.CR 版本更新 50%

VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems

VENOMREC: 多模态交互性污染用于多模态大语言模型推荐系统中的定向推广

Guowei Guan, Yurong Hao, Jiaming Zhang, Tiantong Wu, Fuyao Zhang, Tianxiang Chen, Longtao Huang, Cyril Leung, Wei Yang Bryan Lim

专题命中越狱攻击：alignment(abstract)

AI总结 VENOMREC通过跨模态交互性污染技术，在多模态大语言模型推荐系统中实现定向推广，有效提升推荐性能。

1. 越狱攻击 1731 篇

Multivariable Fractional Polynomials for lithium-ion batteries degradation models under dynamic conditions

HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing

Data-driven Operation of the Resilient Electric Grid: A Case of COVID-19

Smart Band: An Integrated Device for Emergency Management

Explaining Network Intrusion Detection System Using Explainable AI Framework

SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications

Unsupervised Intrusion Detection System for Unmanned Aerial Vehicle with Less Labeling Effort

QEBA: Query-Efficient Boundary-Based Blackbox Attack

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Semisupervised Adversarial Neural Networks for Cyber Security Transfer Learning

The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks

ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector

Prior Networks for Detection of Adversarial Attacks

Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networks

Enhanced Attacks on Defensively Distilled Deep Neural Networks

Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight

On Discrete Prompt Optimization for Diffusion Models

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models

Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer

Autonomous Cyber Defense in Connected Vehicles: A Multi-Agent Approach to V2X Security

PROVE: Training-Free Prompt Recovery using Verifiable Evidence

SoK: The Attack Surface of Agentic AI - Tools and Autonomy

Cross-Layer Semantic Flow Reconstruction for Attack Detection in Agentic Systems

Poisoning Prompt-Guided Sampling in Video Large Language Models

SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks

From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs

Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks

When HTTP 402 Meets the Blockchain: Risks on Emerging x402 Payments

VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems