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)

3,961 to 4,020 of 4,560

Distillation Defenses Easily Break After Reinforcement Learning
Shidan Javaheri, Alexander Panfilov, Oliver Britton +2
cs.LGcs.AIcs.CRarXiv:2609.35699v12026
AI Safety vs. AI Security: Demystifying the Distinction and Boundaries
Zhiqiang Lin, Huan Sun, Ness Shroff
cs.CYcs.AIcs.CRarXiv:2506.18932v12025
A Large-Scale Empirical Study of Modern Phishing Email Content
Jaehwan Park, Woonghee Lee, Fujiao Ji +1
cs.CRarXiv:2609.30683v12026
Summaries:한국어
Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control
Ka-Ho Chow, Wenqi Wei, Lei Yu
cs.CRcs.LGarXiv:2401.01085v22024
Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs
Chetan Pathade
cs.CRcs.CLarXiv:2505.04806v22025
MCP Guardian: A Security-First Layer for Safeguarding MCP-Based AI System
Sonu Kumar, Anubhav Girdhar, Ritesh Patil +1
cs.CRcs.AIarXiv:2504.12757v22025
From Fleet to Lab: Revisiting the Security and Complexity of Industrial Rowhammer Mitigation
Hritvik Taneja, Moinuddin Qureshi
cs.CRcs.ARarXiv:2608.26072v12026
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Kalpesh Krishna, Yixiao Song, Marzena Karpinska +2
cs.CLcs.CRcs.LGarXiv:2303.13408v22023
Attacking the DeFi Ecosystem with Flash Loans for Fun and Profit
Kaihua Qin, Liyi Zhou, Benjamin Livshits +1
cs.CRcs.DCarXiv:2003.03810v42020
A Survey on Essential Components of a Self-Sovereign Identity
Alexander Mühle, Andreas Grüner, Tatiana Gayvoronskaya +1
cs.CRarXiv:1807.06346v12018
A Survey on Wireless Sensor Network Security
Jaydip Sen
cs.CRcs.NIarXiv:1011.1529v12010
Crypto-bound identity-verified capability tokens for coordinating distributed AI agents: A proposal
Srikumar Subramanian, Shubhashis Sengupta
cs.CRarXiv:2609.30824v12026
EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifiers
Robert J. Joyce, Gideon Miller, Phil Roth +5
cs.CRcs.LGarXiv:2506.05074v12025
Toward verifiably private learning from federated data
Katharine Daly, Yu Xiao, Zachary Garrett +9
cs.CRarXiv:2609.31494v12026
Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)
Iyiola E. Olatunji, Franziska Boenisch, Jing Xu +1
cs.CRcs.AIcs.SIarXiv:2508.04894v12025
Combating Phone Scams with LLM-based Detection: Where Do We Stand?
Zitong Shen, Kangzhong Wang, Youqian Zhang +2
cs.CRcs.AIcs.CYarXiv:2409.11643v22024
Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies
Manojkumar Parmar, Yuvaraj Govindarajulu
cs.LGcs.AIcs.CLarXiv:2501.17030v12025
Ghera: A Repository of Android App Vulnerability Benchmarks
Joydeep Mitra, Venkatesh-Prasad Ranganath
cs.CRcs.SEarXiv:1708.02380v12017
Augmenting Greybox Fuzzing with Generative AI
Jie Hu, Qian Zhang, Heng Yin
cs.CRcs.AIarXiv:2306.06782v12023
Configuration, Not Conscience: A Large-Scale Empirical Study of LLM System Prompts
Constantinos Patsakis, Vasilios Argyropoulos, Efthymios Alepis
cs.CRarXiv:2609.31575v12026
Robust Physical-World Attacks on Deep Learning Models
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes +6
cs.CRcs.LGarXiv:1707.08945v52017
FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models
Haoyang Li, Ruoxi Sun, Qingqing Ye +4
cs.CRcs.CVarXiv:2609.30980v12026
AGATE: Provenance-Based Runtime Defense Against Compositional Attacks on LLM Agents
Xiaorui Zhang, Zhuoran Cheng, Kailin Liu +6
cs.CRcs.SEarXiv:2609.30830v12026
The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution
Norbert Tihanyi, Bilel Cherif, Richard A. Dubniczky +2
cs.CRcs.LGarXiv:2510.10493v22025
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
Boyang Zhang, Yicong Tan, Yun Shen +4
cs.CRcs.LGarXiv:2407.20859v12024
Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
Dongxian Wu, Yisen Wang, Shu-Tao Xia +2
cs.LGcs.CRcs.CVarXiv:2002.05990v12020
Adversarial Reprogramming of Neural Networks
Gamaleldin F. Elsayed, Ian Goodfellow, Jascha Sohl-Dickstein
cs.LGcs.CRcs.CVarXiv:1806.11146v22018
Autonomous Cyber Defense: Real-Time Attack Detection and Mitigation in Software-Defined Networks Using Machine Learning
Alexandre Amaral, Fernando Moro, Ana Malheiro
cs.CRcs.LGarXiv:2608.22075v32026
Unconditional security from noisy quantum storage
Robert Koenig, Stephanie Wehner, Juerg Wullschleger
quant-phcs.CRarXiv:0906.1030v42009
DP-VOXLET: Provable Speaker Anonymization for Disentangled Speech Representations
Ivoline Ngong, Jack D'Iorio, Hailey Schoppe +4
cs.CRarXiv:2608.30969v12026
Zero Trust Architecture: A Systematic Literature Review
Muhammad Liman Gambo, Ahmad Almulhem
cs.CRarXiv:2503.11659v22025
Efficient Decision-based Black-box Adversarial Attacks on Face Recognition
Yinpeng Dong, Hang Su, Baoyuan Wu +4
cs.CVcs.CRcs.LGarXiv:1904.04433v12019
Secure Evaluation of Quantized Neural Networks
Anders Dalskov, Daniel Escudero, Marcel Keller
cs.CRcs.LGarXiv:1910.12435v22019
Decentralization in Bitcoin and Ethereum Networks
Adem Efe Gencer, Soumya Basu, Ittay Eyal +2
cs.CRarXiv:1801.03998v22018
HermiCache: Enclave-Aware Cache Replacement for Trusted Execution Environments
Oussama Elmnaouri, Pascal Cotret, Vianney Lapôtre +1
cs.CRcs.ARarXiv:2609.10634v12026
ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation
Qingyu Wu, Zeyu Feng, Yongda Yu +2
cs.AIcs.CRarXiv:2609.29948v12026
ClaimMirage: When Self-Claims in Domain Names Change LLM Threat Judgments
Daiki Chiba, Hiroki Nakano, Takashi Koide
cs.CRarXiv:2609.29130v12026
Few-Shot Learning for Network Intrusion Detection: Methods, Datasets, and Performance
Arne Roszeitis, Victor Jüttner, Erik Buchmann
cs.CRarXiv:2609.11275v12026
Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports
Akash Prakash, Boubakr Nour, Makan Pourzandi +2
cs.CRcs.AIarXiv:2609.08790v12026
Template Ageing and Longitudinal Verification in Fixed-Text Keystroke Dynamics: A Subject-Disjoint Study Across Eight Weeks
Simon Parkinson, Saad Khan, Na Liu +1
cs.CRcs.AIarXiv:2609.29851v12026
A Corpus of Real Scam- and Spam-Call Conversations from an Active Voice-Agent Honeypot
Ethan Traister, Dennis Tsang Ng, Siyu Zhang +7
cs.CRcs.CLcs.LGarXiv:2609.29528v12026
The History Is the Detector: Executing CVE Patch History, End-to-End
Qiushi Wu, Kevin Eykholt, Youngja Park +4
cs.CRcs.AIcs.SEarXiv:2609.05335v12026
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
A TTP by TTP Approach: Precise Malware Detection via Malicious TTP Recognition
Yashovardhan Sharma
cs.CRcs.AIarXiv:2609.06579v12026
Memory-Efficient Designs for Word-Wise Universal Fully Homomorphic Encryption
Ardhi Wiratama Baskara Yudha, Erwin Eko Wahyudi, Rian Adam Rajagede +2
cs.CRarXiv:2609.04769v12026
StepTrigger: Contact-State-Triggered Backdoor Attacks on VLM-Powered Legged Robots
Jiageng Zhang, Doniyorkhon Obidov, Kaichen Yang
cs.ROcs.AIcs.CRarXiv:2609.26131v12026
Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics
Yijie Lin, Ching-Chun Chang, Isao Echizen +2
cs.CRcs.AIcs.CVarXiv:2609.02268v12026
Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models
Tianqi Xiao, Shiyao Cui, Minghao Zhang +2
cs.MMcs.AIcs.CLarXiv:2609.02082v12026
Don't Trust the Code, Check Its Effects: Runtime Refinement for Regenerated Systems Code Under an Adversarial Generator
Jinhao Hu, Ashvin Goel, Laurent Bindschaedler
cs.CRarXiv:2609.00430v12026
In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning
Iliano Fasolino
cs.CRcs.AIcs.CLarXiv:2609.09243v12026
When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning
Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2
cs.CRcs.AIarXiv:2609.01455v12026
Big Enough to Break Out: Tracking the Rising Capability of LLM Penetration-Testing Agents
Victoria Lovelace, Cameron Berryman, Yuhan You +3
cs.CRarXiv:2609.10780v12026
Watermarks Without Verification: AI Text Watermarking After the EU AI Act
Alexander Nemecek, Vipin Chaudhary, Erman Ayday
cs.CYcs.AIcs.CRarXiv:2609.09604v12026
When Verified Source Becomes Attack Input: Defending Smart Contracts Against LLM-Based Vulnerability Scanning
Mingyuan Huang, Zimo Ji, Yifan Mo +1
cs.CRcs.SEarXiv:2608.28400v12026
False-CSI Attacks in Power-Domain NOMA for 6G: A Threat Taxonomy and System-Level Impacts
Samira Jafarli, Aysha Ebrahim, Suleyman Uludag
cs.CReess.SParXiv:2608.28351v12026
An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
Viet K. Nguyen, Mohammad I. Husain
cs.CRcs.AIarXiv:2609.09404v12026
Offline-Verifiable Accountability for Cross-Organization Agent Messaging: A Preserved Evidence-Bundle Approach
Adil Alshammari, Hayretdin Bahsi
cs.CRcs.MAarXiv:2608.28542v12026
Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach?
Ting Yan
cs.HCcs.CRarXiv:2608.27443v12026
SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure
Qi Wang, Chengcheng Wan, Jiangtao Wang
cs.CRcs.AIarXiv:2609.06540v12026
KubeCap: A Framework for Capability Minimization in Kubernetes via Static Analysis and LLM-Assisted Rule Inference
Yuhao Liu, Yingnan Zhou, Weijie Liu +2
cs.CRcs.SEarXiv:2608.26699v12026

Cryptography and Security

Distillation Defenses Easily Break After Reinforcement Learning

AI Safety vs. AI Security: Demystifying the Distinction and Boundaries

A Large-Scale Empirical Study of Modern Phishing Email Content

Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

MCP Guardian: A Security-First Layer for Safeguarding MCP-Based AI System

From Fleet to Lab: Revisiting the Security and Complexity of Industrial Rowhammer Mitigation

Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense

Attacking the DeFi Ecosystem with Flash Loans for Fun and Profit

A Survey on Essential Components of a Self-Sovereign Identity

A Survey on Wireless Sensor Network Security

Crypto-bound identity-verified capability tokens for coordinating distributed AI agents: A proposal

EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifiers

Toward verifiably private learning from federated data

Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)

Combating Phone Scams with LLM-based Detection: Where Do We Stand?

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies

Ghera: A Repository of Android App Vulnerability Benchmarks

Augmenting Greybox Fuzzing with Generative AI

Configuration, Not Conscience: A Large-Scale Empirical Study of LLM System Prompts

Robust Physical-World Attacks on Deep Learning Models

FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models

AGATE: Provenance-Based Runtime Defense Against Compositional Attacks on LLM Agents

The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution

Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

Adversarial Reprogramming of Neural Networks

Autonomous Cyber Defense: Real-Time Attack Detection and Mitigation in Software-Defined Networks Using Machine Learning

Unconditional security from noisy quantum storage

DP-VOXLET: Provable Speaker Anonymization for Disentangled Speech Representations

Zero Trust Architecture: A Systematic Literature Review

Efficient Decision-based Black-box Adversarial Attacks on Face Recognition

Secure Evaluation of Quantized Neural Networks

Decentralization in Bitcoin and Ethereum Networks

HermiCache: Enclave-Aware Cache Replacement for Trusted Execution Environments

ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation

ClaimMirage: When Self-Claims in Domain Names Change LLM Threat Judgments

Few-Shot Learning for Network Intrusion Detection: Methods, Datasets, and Performance

Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports

Template Ageing and Longitudinal Verification in Fixed-Text Keystroke Dynamics: A Subject-Disjoint Study Across Eight Weeks

A Corpus of Real Scam- and Spam-Call Conversations from an Active Voice-Agent Honeypot

The History Is the Detector: Executing CVE Patch History, End-to-End

TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors

A TTP by TTP Approach: Precise Malware Detection via Malicious TTP Recognition

Memory-Efficient Designs for Word-Wise Universal Fully Homomorphic Encryption

StepTrigger: Contact-State-Triggered Backdoor Attacks on VLM-Powered Legged Robots

Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics

Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models

Don't Trust the Code, Check Its Effects: Runtime Refinement for Regenerated Systems Code Under an Adversarial Generator

In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning

When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

Big Enough to Break Out: Tracking the Rising Capability of LLM Penetration-Testing Agents

Watermarks Without Verification: AI Text Watermarking After the EU AI Act

When Verified Source Becomes Attack Input: Defending Smart Contracts Against LLM-Based Vulnerability Scanning

False-CSI Attacks in Power-Domain NOMA for 6G: A Threat Taxonomy and System-Level Impacts

An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks

Offline-Verifiable Accountability for Cross-Organization Agent Messaging: A Preserved Evidence-Bundle Approach

Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach?

SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure

KubeCap: A Framework for Capability Minimization in Kubernetes via Static Analysis and LLM-Assisted Rule Inference