Cryptography and Security

Papers filed under cs.CR on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

781 to 840 of 2,549

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
Yunhao Feng, Yifan Ding, Yingshui Tan +6
cs.CRcs.AIarXiv:2604.06811v22026
Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding
Kejia Zhang, Tianyuan Zou, Zixuan GU +1
cs.CRcs.AIarXiv:2608.29111v12026
A Multi-Month Study of Git Commit Signing
Abubakar Sadiq Shittu, John Sadik, Scott Ruoti
cs.CRcs.SEarXiv:2608.29283v12026
Contextual Agent Security: A Policy for Every Purpose
Lillian Tsai, Eugene Bagdasarian
cs.CRcs.CLcs.LGarXiv:2501.17070v32025
Formal Policy Enforcement for Real-World Agentic Systems
Nils Palumbo, Sarthak Choudhary, Jihye Choi +3
cs.CRcs.AIcs.MAarXiv:2602.16708v32026
InstaHide: Instance-hiding Schemes for Private Distributed Learning
Yangsibo Huang, Zhao Song, Kai Li +1
cs.CRcs.CCcs.DSarXiv:2010.02772v22020
Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents
Vineeth Sai Narajala, Om Narayan
cs.CRcs.AIarXiv:2504.19956v22025
Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems
Narek Maloyan, Dmitry Namiot
cs.CRarXiv:2601.17548v12026
UiAs: User-Independent 3D Facial Anti-Spoofing via Multi-modal Wireless Signals
Zhiwei chen, Lebin Lyu, Yimo Zhang +7
cs.CRarXiv:2608.29084v12026
BlendCAC: A BLockchain-ENabled Decentralized Capability-based Access Control for IoTs
Ronghua Xu, Yu Chen, Erik Blasch +1
cs.NIcs.CRcs.DCarXiv:1804.09267v12018
Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents
Yuandao Cai, Wensheng Tang, Cheng Wen +1
cs.CRarXiv:2604.23374v12026
Getting pwn'd by AI: Penetration Testing with Large Language Models
Andreas Happe, Jürgen Cito
cs.CLcs.AIcs.CRarXiv:2308.00121v32023
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
Pritam Dash, Tongyu Ge, Aditi Jain +2
cs.CRcs.AIarXiv:2606.04329v22026
Certified randomness using a trapped-ion quantum processor
Minzhao Liu, Ruslan Shaydulin, Pradeep Niroula +29
quant-phcs.CRcs.ETarXiv:2503.20498v12025
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Hoagy Cunningham, Jerry Wei, Zihan Wang +26
cs.CRcs.AIarXiv:2601.04603v12026
SoK: Decentralized Finance (DeFi) Attacks
Liyi Zhou, Xihan Xiong, Jens Ernstberger +7
cs.CRarXiv:2208.13035v32022
"Humans welcome to observe": A First Look at the Agent Social Network Moltbook
Yukun Jiang, Yage Zhang, Xinyue Shen +2
cs.SIcs.AIcs.CRarXiv:2602.10127v12026
A Survey on Privacy Risks and Protection in Large Language Models
Kang Chen, Xiuze Zhou, Yuanguo Lin +3
cs.CRarXiv:2505.01976v12025
A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
Mang Ye, Xuankun Rong, Wenke Huang +3
cs.CRcs.CVarXiv:2502.14881v12025
Functionality-preserving Black-box Optimization of Adversarial Windows Malware
Luca Demetrio, Battista Biggio, Giovanni Lagorio +2
cs.CRarXiv:2003.13526v42020
Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using Agents
Laurent Bindschaedler, Quentin Botha, Christoph Siebenbrunner
cs.CRcs.MAarXiv:2609.01931v12026
Invisible Image Watermarks Are Provably Removable Using Generative AI
Xuandong Zhao, Kexun Zhang, Zihao Su +6
cs.CRcs.AIcs.CVarXiv:2306.01953v32023
Graphical-model based estimation and inference for differential privacy
Ryan McKenna, Daniel Sheldon, Gerome Miklau
cs.LGcs.CRstat.MLarXiv:1901.09136v12019
ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse
Jongmin Kim, Gwangho Lee, Sangpyo Kim +4
cs.CRcs.ARarXiv:2205.00922v32022
Trading Inference-Time Compute for Adversarial Robustness
Wojciech Zaremba, Evgenia Nitishinskaya, Boaz Barak +8
cs.LGcs.CRarXiv:2501.18841v12025
Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
Zhengyang Shan, Jiayun Xin, Yue Zhang +1
cs.CRarXiv:2603.10387v12026
The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections
Chaoran Chen, Zhiping Zhang, Bingcan Guo +8
cs.HCcs.CLcs.CRarXiv:2504.11281v12025
Privacy in geo-social networks: proximity notification with untrusted service providers and curious buddies
Sergio Mascetti, Dario Freni, Claudio Bettini +2
cs.DBcs.CRarXiv:1007.0408v22010
Machine Learning for the Detection and Identification of Internet of Things (IoT) Devices: A Survey
Yongxin Liu, Jian Wang, Jianqiang Li +2
cs.CRcs.AIcs.LGarXiv:2101.10181v12021
Position: Privacy Is a Claim, Not a Property of Synthetic Data
Jiachen Zhao, Antonia Januszewicz, Taeho Jung
cs.LGcs.CRarXiv:2609.01273v12026
Tiresias: Predicting Security Events Through Deep Learning
Yun Shen, Enrico Mariconti, Pierre-Antoine Vervier +1
cs.CRcs.LGarXiv:1905.10328v12019
Detection of Early-Stage Enterprise Infection by Mining Large-Scale Log Data
Alina Oprea, Zhou Li, Ting-Fang Yen +2
cs.CRarXiv:1411.5005v22014
Securing Elliptic Curve Cryptocurrencies against Quantum Vulnerabilities: Resource Estimates and Mitigations
Ryan Babbush, Adam Zalcman, Craig Gidney +6
quant-phcs.CRarXiv:2603.28846v22026
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Shiji Zhao, Ranjie Duan, Fengxiang Wang +7
cs.CRcs.AIcs.CLarXiv:2501.04931v22025
SybilBelief: A Semi-supervised Learning Approach for Structure-based Sybil Detection
Neil Zhenqiang Gong, Mario Frank, Prateek Mittal
cs.CRcs.SIarXiv:1312.5035v22013
Can Indirect Prompt Injection Attacks Be Detected and Removed?
Yulin Chen, Haoran Li, Yuan Sui +4
cs.CRarXiv:2502.16580v52025
Feature Extraction for Machine Learning-based Intrusion Detection in IoT Networks
Mohanad Sarhan, Siamak Layeghy, Nour Moustafa +2
cs.NIcs.CRcs.LGarXiv:2108.12722v32021
Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
Xianglin Yang, Yufei He, Shuo Ji +2
cs.CRcs.AIarXiv:2602.15654v22026
A Formal Analysis of Agent Payment Protocols
Ke Jiang, Mohan Yu, Yuan Chang +4
cs.CRcs.AIarXiv:2609.00060v12026
Comparative Analysis Based on DeepSeek, ChatGPT, and Google Gemini: Features, Techniques, Performance, Future Prospects
Anichur Rahman, Shahariar Hossain Mahir, Md Tanjum An Tashrif +6
cs.CLcs.CRarXiv:2503.04783v12025
Conclave: secure multi-party computation on big data (extended TR)
Nikolaj Volgushev, Malte Schwarzkopf, Ben Getchell +3
cs.CRarXiv:1902.06288v12019
Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection
Wujie Xiong, Rabimba Karanjai, Yang Lu +2
cs.CRcs.AIarXiv:2608.30041v12026
Zero Trust Architecture: A Systematic Literature Review
Muhammad Liman Gambo, Ahmad Almulhem
cs.CRarXiv:2503.11659v22025
Enhancing Web Application Firewalls with BERT-GNN for SQL Injection Detection
Lilliane Linnet Musoke, Atta Badii, Ahmed Ashlam
cs.CRarXiv:2608.28882v12026
Enhancing Web Application Firewalls with Machine Learning for SQL Injection Detection
Lilliane Linnet Musoke, Atta Badii, Ahmed Ashlam
cs.CRarXiv:2608.28889v12026
JITterFlip: Uncovering Fault Attack Surfaces in JIT-Compiled LLM Serving
Tairui Wang, Zhi Zhang, Yansong Gao +3
cs.CRarXiv:2608.29745v12026
MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols
Yixuan Yang, Cuifeng Gao, Daoyuan Wu +3
cs.CRcs.AIarXiv:2508.13220v32025
Reactive Peripheral Modeling for Faithful Firmware Rehosting
Qinying Wang, Florian Hofhammer, Eduard Vlad +4
cs.CRarXiv:2608.29737v12026
EvoFlint: An Evolutionary Atlas of Multi-Turn LLM Vulnerabilities
Feitong Qiao, Liren Peng, Shiming Ren +7
cs.CLcs.AIcs.CRarXiv:2609.00487v12026
Workload Identification with Physical Side Channels for AI Governance
Simone Gargiulo, Gabriel Kulp
cs.CRcs.AIcs.CYarXiv:2609.00309v12026
Membership is Ownership: A Robust Ownership Verification Framework for Diffusion Models
Feng Jiang, Zuobin Xiong, An Huang +2
cs.CRcs.CVarXiv:2608.28929v12026
RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
Peter Yong Zhong, Siyuan Chen, Ruiqi Wang +4
cs.CRcs.AIarXiv:2502.08966v22025
ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
Wei Zhao, Zhe Li, Peixin Zhang +1
cs.CRcs.AIarXiv:2604.11790v22026
Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network
Xuanqing Liu, Yao Li, Chongruo Wu +1
cs.LGcs.AIcs.CRarXiv:1810.01279v22018
Enterprise-Grade Security for the Model Context Protocol (MCP): Frameworks and Mitigation Strategies
Vineeth Sai Narajala, Idan Habler
cs.CRcs.AIarXiv:2504.08623v22025
Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
Juhee Kim, Woohyuk Choi, Byoungyoung Lee
cs.CRcs.AIcs.MAarXiv:2503.15547v22025
Blockchain-Based Decentralized Energy Management Platform for Residential Distributed Energy Resources in A Virtual Power Plant
Qing Yang, Hao Wang, Taotao Wang +3
eess.SYcs.CRcs.DCarXiv:2105.00174v22021
ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
Zhun Wang, Nico Schiller, Hongwei Li +13
cs.CRcs.AIcs.LGarXiv:2605.11086v12026
CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
Zhun Wang, Tianneng Shi, Jingxuan He +3
cs.CRcs.AIcs.LGarXiv:2506.02548v32025
Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories
Alperen Yildiz, Sin G. Teo, Yiling Lou +3
cs.CRarXiv:2503.03586v22025

Cryptography and Security

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding

A Multi-Month Study of Git Commit Signing

Contextual Agent Security: A Policy for Every Purpose

Formal Policy Enforcement for Real-World Agentic Systems

InstaHide: Instance-hiding Schemes for Private Distributed Learning

Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents

Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems

UiAs: User-Independent 3D Facial Anti-Spoofing via Multi-modal Wireless Signals

BlendCAC: A BLockchain-ENabled Decentralized Capability-based Access Control for IoTs

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Getting pwn'd by AI: Penetration Testing with Large Language Models

From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

Certified randomness using a trapped-ion quantum processor

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks

SoK: Decentralized Finance (DeFi) Attacks

"Humans welcome to observe": A First Look at the Agent Social Network Moltbook

A Survey on Privacy Risks and Protection in Large Language Models

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations

Functionality-preserving Black-box Optimization of Adversarial Windows Malware

Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using Agents

Invisible Image Watermarks Are Provably Removable Using Generative AI

Graphical-model based estimation and inference for differential privacy

ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse

Trading Inference-Time Compute for Adversarial Robustness

Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw

The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Privacy in geo-social networks: proximity notification with untrusted service providers and curious buddies

Machine Learning for the Detection and Identification of Internet of Things (IoT) Devices: A Survey

Position: Privacy Is a Claim, Not a Property of Synthetic Data

Tiresias: Predicting Security Events Through Deep Learning

Detection of Early-Stage Enterprise Infection by Mining Large-Scale Log Data

Securing Elliptic Curve Cryptocurrencies against Quantum Vulnerabilities: Resource Estimates and Mitigations

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

SybilBelief: A Semi-supervised Learning Approach for Structure-based Sybil Detection

Can Indirect Prompt Injection Attacks Be Detected and Removed?

Feature Extraction for Machine Learning-based Intrusion Detection in IoT Networks

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections

A Formal Analysis of Agent Payment Protocols

Comparative Analysis Based on DeepSeek, ChatGPT, and Google Gemini: Features, Techniques, Performance, Future Prospects

Conclave: secure multi-party computation on big data (extended TR)

Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection

Zero Trust Architecture: A Systematic Literature Review

Enhancing Web Application Firewalls with BERT-GNN for SQL Injection Detection

Enhancing Web Application Firewalls with Machine Learning for SQL Injection Detection

JITterFlip: Uncovering Fault Attack Surfaces in JIT-Compiled LLM Serving

MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols

Reactive Peripheral Modeling for Faithful Firmware Rehosting

EvoFlint: An Evolutionary Atlas of Multi-Turn LLM Vulnerabilities

Workload Identification with Physical Side Channels for AI Governance

Membership is Ownership: A Robust Ownership Verification Framework for Diffusion Models

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection

Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network

Enterprise-Grade Security for the Model Context Protocol (MCP): Frameworks and Mitigation Strategies

Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents

Blockchain-Based Decentralized Energy Management Platform for Residential Distributed Energy Resources in A Virtual Power Plant

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale

Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories