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)

601 to 660 of 2,547

AgentGuardian: Learning Access Control Policies to Govern AI Agent Behavior
Nadya Abaev, Denis Klimov, Gerard Levinov +3
cs.CRcs.AIcs.LGarXiv:2601.10440v12026
On Covert Acoustical Mesh Networks in Air
Michael Hanspach, Michael Goetz
cs.CRcs.NIcs.SDarXiv:1406.1213v12014
TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents
Yibing Liu, Chong Zhang, Zhongyi Han +5
cs.CRcs.AIarXiv:2602.06443v12026
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
Jianqing Zhang, Yang Liu, Yang Hua +1
cs.LGcs.CRcs.DCarXiv:2401.03230v12024
TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors
Thu-Hien Trinh-Thi, Hai-Yen Vong, Thanh-Ha Ung-Dung +1
cs.CRcs.AIarXiv:2609.05117v12026
DECO: Liberating Web Data Using Decentralized Oracles for TLS
Fan Zhang, Sai Krishna Deepak Maram, Harjasleen Malvai +2
cs.CRarXiv:1909.00938v62019
AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
Abdullah Hamdi, Sara Rojas, Ali Thabet +1
cs.CVcs.CRcs.LGarXiv:1912.00461v22019
EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation
Roshan Dathathri, Blagovesta Kostova, Olli Saarikivi +3
cs.CRcs.LGcs.PLarXiv:1912.11951v22019
MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
Georgios Syros, Evan Rose, Brian Grinstead +4
cs.CRcs.AIarXiv:2602.09222v22026
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
Chao Yao, Yangbo Wei, Zhen Huang +5
cs.CRcs.AIarXiv:2609.04875v12026
Label Leakage and Protection in Two-party Split Learning
Oscar Li, Jiankai Sun, Xin Yang +5
cs.LGcs.CRarXiv:2102.08504v32021
ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification
Jieyun Huang, Yi Shen, Kaikai Zhao +7
cs.CRcs.AIarXiv:2609.04878v12026
Adversarial Example Detection for DNN Models: A Review and Experimental Comparison
Ahmed Aldahdooh, Wassim Hamidouche, Sid Ahmed Fezza +1
cs.CVcs.CRarXiv:2105.00203v42021
Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution
Mubashar Iqbal, Asifullah Khan
cs.CRcs.AIarXiv:2609.04820v12026
ARIstoteles -- Dissecting Apple's Baseband Interface
Tobias Kröll, Stephan Kleber, Frank Kargl +2
cs.CRcs.NIarXiv:2604.23457v12026
What Physical Layer Security Can Do for 6G Security
Miroslav Mitev, Arsenia Chorti, H. V. Poor +1
cs.CRarXiv:2212.00427v12022
Exploiting Channel Diversity in Secret Key Generation from Multipath Fading Randomness
Yanpei Liu, Stark C. Draper, Akbar M. Sayeed
cs.CRcs.ITarXiv:1107.3534v22011
Optimal quantitative cryptanalysis of permutation-only multimedia ciphers against plaintext attacks
Chengqing Li, Kwok-Tung Lo
cs.CRarXiv:0912.1918v32009
PIArena: A Platform for Prompt Injection Evaluation
Runpeng Geng, Chenlong Yin, Yanting Wang +2
cs.CRcs.AIcs.CLarXiv:2604.08499v12026
MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
Ruiqi Li, Zhiqiang Wang, Yunhao Yao +1
cs.CRcs.AIarXiv:2601.07395v12026
On the `Semantics' of Differential Privacy: A Bayesian Formulation
Shiva Prasad Kasiviswanathan, Adam Smith
cs.CRcs.DBarXiv:0803.3946v42008
Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
Kaiyu Zhou, Yongsen Zheng, Yicheng He +5
cs.CRcs.AIarXiv:2601.10955v22026
Data Poisoning against Differentially-Private Learners: Attacks and Defenses
Yuzhe Ma, Xiaojin Zhu, Justin Hsu
cs.LGcs.CRarXiv:1903.09860v22019
The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
Blake Bullwinkel, Giorgio Severi, Keegan Hines +3
cs.CRcs.AIarXiv:2602.03085v12026
Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP
Zeynab Anbiaee, Mahdi Rabbani, Mansur Mirani +4
cs.CRcs.AIarXiv:2602.11327v22026
MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection
Ruiqi Liu, Manni Cui, Ziheng Qin +12
cs.CVcs.CRarXiv:2602.02222v12026
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
Zehao Lin, Xixuan Hao, Renyu Fu +5
cs.CRcs.AIcs.CLarXiv:2604.16548v22026
Mining Attribute-Based Access Control Policies from Logs
Zhongyuan Xu, Scott D. Stoller
cs.CRcs.DBarXiv:1403.5715v52014
When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks
Minghao Guo, Yuzhe Yang, Rui Xu +2
cs.LGcs.CRcs.CVarXiv:1911.10695v32019
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
Jaylen Jones, Zhehao Zhang, Yuting Ning +6
cs.CLcs.AIcs.CRarXiv:2602.08235v22026
Applications of Artificial Intelligence Techniques to Combating Cyber Crimes: A Review
Selma Dilek, Hüseyin Çakır, Mustafa Aydın
cs.AIcs.CRcs.CYarXiv:1502.03552v12015
SoK: The Attack Surface of Agentic AI - Tools and Autonomy
Ali Dehghantanha, Sajad Homayoun
cs.CRarXiv:2603.22928v22026
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
Alexander Panfilov, Peter Romov, Igor Shilov +3
cs.LGcs.AIcs.CRarXiv:2603.24511v22026
Is GitHub's Copilot as Bad as Humans at Introducing Vulnerabilities in Code?
Owura Asare, Meiyappan Nagappan, N. Asokan
cs.SEcs.CRarXiv:2204.04741v52022
AgenTRIM: Tool Risk Mitigation for Agentic AI
Roy Betser, Amit Giloni, Shamik Bose +4
cs.CRcs.AIarXiv:2601.12449v22026
Link Prediction by De-anonymization: How We Won the Kaggle Social Network Challenge
Arvind Narayanan, Elaine Shi, Benjamin I. P. Rubinstein
cs.CRcs.LGarXiv:1102.4374v12011
Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
Hongyan Chang, Ergute Bao, Xinjian Luo +1
cs.CRcs.AIarXiv:2601.07072v12026
From Storage to Steering: Memory Control Flow Attacks on LLM Agents
Zhenlin Xu, Xiaogang Zhu, Yu Yao +2
cs.CRarXiv:2603.15125v32026
SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
Yinghan Hou, Zongyou Yang
cs.CRcs.AIarXiv:2604.06550v32026
AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
Yihao Zhang, Zeming Wei, Xiaokun Luan +7
cs.CRcs.AIcs.LGarXiv:2603.15727v32026
Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability
Yifeng Xiong, Jiadong Lin, Min Zhang +2
cs.LGcs.CRcs.CVarXiv:2111.10752v22021
The Web-CLI: Verifiable Privacy for Tools, Models, and Inference Engines in the Browser
Tejaswi Gowda
cs.HCcs.CRcs.SEarXiv:2608.28950v22026
OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
Xin Wang, Yunhao Chen, Juncheng Li +7
cs.CRcs.CVarXiv:2601.01592v22026
An Empirical Analysis of Anonymity in Zcash
George Kappos, Haaroon Yousaf, Mary Maller +1
cs.CRarXiv:1805.03180v12018
PLeak: Prompt Leaking Attacks against Large Language Model Applications
Bo Hui, Haolin Yuan, Neil Gong +2
cs.CRcs.AIcs.LGarXiv:2405.06823v32024
SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
Xiaojun Jia, Jie Liao, Simeng Qin +5
cs.CRcs.AIarXiv:2602.14211v32026
Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
Manish Bhatt, Sahana Chennabasappa, Cyrus Nikolaidis +18
cs.CRcs.LGarXiv:2312.04724v12023
Winning the NIST Contest: A scalable and general approach to differentially private synthetic data
Ryan McKenna, Gerome Miklau, Daniel Sheldon
cs.CRarXiv:2108.04978v12021
Not the Same Protector: Deployment-Dependent Protective Intervention in LLMs
Eunna Lee, Soomyoung Lee, Jungpyo Nam +6
cs.CRcs.AIarXiv:2608.29136v12026
Physical Unclonable Functions (PUF) for IoT Devices
Abdulaziz Al-Meer, Saif Al-Kuwari
cs.CRarXiv:2205.08587v12022
More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence
Tianqing Zhu, Dayong Ye, Wei Wang +2
cs.CRcs.LGstat.MLarXiv:2008.01916v12020
Differential Privacy for Industrial Internet of Things: Opportunities, Applications and Challenges
Bin Jiang, Jianqiang Li, Guanghui Yue +1
cs.CRarXiv:2101.10569v32021
GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models
Zuyao Xu, Yuqi Qiu, Lu Sun +14
cs.CRcs.AIarXiv:2602.06718v22026
Satellite-Based Communications Security: A Survey of Threats, Solutions, and Research Challenges
Pietro Tedeschi, Savio Sciancalepore, Roberto Di Pietro
cs.CRcs.NIarXiv:2112.11324v42021
Towards Developing Network forensic mechanism for Botnet Activities in the IoT based on Machine Learning Techniques
Nickolaos Koroniotis, Nour Moustafa, Elena Sitnikova +1
cs.CRarXiv:1711.02825v12017
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
Rahul Marchand, Art O Cathain, Jerome Wynne +8
cs.CRcs.AIarXiv:2603.02277v32026
How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
Zhihao Chen, Ying Zhang, Yi Liu +7
cs.CRcs.AIarXiv:2604.03070v22026
A Systematic Security Evaluation of OpenClaw and Its Variants
Yuhang Wang, Haichang Gao, Zhenxing Niu +4
cs.CRcs.AIarXiv:2604.03131v12026
Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis
Zhiyuan Li, Jingzheng Wu, Xiang Ling +2
cs.CRcs.AIarXiv:2604.02837v12026
Building the Truman Show: A TrustZone-Based Framework for Lightweight Out-of-band Kernel Security Monitoring
Zhenling Duan, Pan Dong, Renshuang Jiang +2
cs.CRcs.SEarXiv:2608.29758v12026

Cryptography and Security

AgentGuardian: Learning Access Control Policies to Govern AI Agent Behavior

On Covert Acoustical Mesh Networks in Air

TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents

FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning

TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors

DECO: Liberating Web Data Using Decentralized Oracles for TLS

AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds

EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

Label Leakage and Protection in Two-party Split Learning

ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification

Adversarial Example Detection for DNN Models: A Review and Experimental Comparison

Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution

ARIstoteles -- Dissecting Apple's Baseband Interface

What Physical Layer Security Can Do for 6G Security

Exploiting Channel Diversity in Secret Key Generation from Multipath Fading Randomness

Optimal quantitative cryptanalysis of permutation-only multimedia ciphers against plaintext attacks

PIArena: A Platform for Prompt Injection Evaluation

MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP

On the `Semantics' of Differential Privacy: A Bayesian Formulation

Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents

Data Poisoning against Differentially-Private Learners: Attacks and Defenses

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP

MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection

A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle

Mining Attribute-Based Access Control Policies from Logs

When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks

When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents

Applications of Artificial Intelligence Techniques to Combating Cyber Crimes: A Review

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

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

Is GitHub's Copilot as Bad as Humans at Introducing Vulnerabilities in Code?

AgenTRIM: Tool Risk Mitigation for Agentic AI

Link Prediction by De-anonymization: How We Won the Kaggle Social Network Challenge

Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems

From Storage to Steering: Memory Control Flow Attacks on LLM Agents

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills

AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability

The Web-CLI: Verifiable Privacy for Tools, Models, and Inference Engines in the Browser

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs

An Empirical Analysis of Anonymity in Zcash

PLeak: Prompt Leaking Attacks against Large Language Model Applications

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents

Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Winning the NIST Contest: A scalable and general approach to differentially private synthetic data

Not the Same Protector: Deployment-Dependent Protective Intervention in LLMs

Physical Unclonable Functions (PUF) for IoT Devices

More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence

Differential Privacy for Industrial Internet of Things: Opportunities, Applications and Challenges

GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models

Satellite-Based Communications Security: A Survey of Threats, Solutions, and Research Challenges

Towards Developing Network forensic mechanism for Botnet Activities in the IoT based on Machine Learning Techniques

Quantifying Frontier LLM Capabilities for Container Sandbox Escape

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

A Systematic Security Evaluation of OpenClaw and Its Variants

Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis

Building the Truman Show: A TrustZone-Based Framework for Lightweight Out-of-band Kernel Security Monitoring