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)

1 to 60 of 2,547

Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning
Yang Zou, Zhikun Zhang, Michael Backes +1
cs.CRcs.LGstat.MLarXiv:2009.04872v12020
Users really do respond to smishing
Muhammad Lutfor Rahman, Daniel Timko, Hamid Wali +1
cs.CRarXiv:2212.13312v12022
The Claws in Plain Sight: Unauthorized Context Disclosure through LLM Agent Tool Calls
Ben Dong, Zhonghao Guo, Tianyi Lu +1
cs.CRcs.ETarXiv:2608.20658v12026
The Role of Machine Learning in Cybersecurity
Giovanni Apruzzese, Pavel Laskov, Edgardo Montes de Oca +4
cs.CRcs.LGarXiv:2206.09707v12022
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
Yangsibo Huang, Samyak Gupta, Mengzhou Xia +2
cs.CLcs.AIcs.CRarXiv:2310.06987v12023
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Xuan Li, Zhanke Zhou, Jianing Zhu +3
cs.LGcs.CRarXiv:2311.03191v52023
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
Yining Chen, Jihao Zhao, Bo Tang +5
cs.CRcs.CLarXiv:2605.09530v32026
A Survey on Metaverse: Fundamentals, Security, and Privacy
Yuntao Wang, Zhou Su, Ning Zhang +4
cs.CRarXiv:2203.02662v42022
Red Teaming Language Models with Language Models
Ethan Perez, Saffron Huang, Francis Song +6
cs.CLcs.AIcs.CRarXiv:2202.03286v12022
Reconstructing Training Data with Informed Adversaries
Borja Balle, Giovanni Cherubin, Jamie Hayes
cs.CRcs.LGarXiv:2201.04845v22022
LLMSec-AV: A Vulnerability Taxonomy and LLM-Driven Software Weakness Discovery Framework for Autonomous Vehicles
Md. Wasiul Haque, Sagar Dasgupta, Mizanur Rahman
cs.CRarXiv:2609.09386v12026
SPECTECTOR: Principled Detection of Speculative Information Flows
Marco Guarnieri, Boris Köpf, José F. Morales +2
cs.CRarXiv:1812.08639v22018
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
Kimin Lee, Kibok Lee, Honglak Lee +1
stat.MLcs.CRcs.LGarXiv:1807.03888v22018
Griotte: Verified Compartmentalisation via Capabilities
June Rousseau, Aïna Linn Georges, Jean Pichon-Pharabod +1
cs.PLcs.CRarXiv:2609.01110v12026
Casper the Friendly Finality Gadget
Vitalik Buterin, Virgil Griffith
cs.CRarXiv:1710.09437v42017
Exploiting Per-Core Leakage: Electromagnetic Side-Channel Monitoring of Multicore Architectures
Daehyeon Bae, Sujin Park, Insup Lee +4
cs.CRarXiv:2608.28412v12026
Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction
Yu-Lin Tsai, Yu-An Lu, Ci-Yang Tsai +3
cs.CRcs.AIcs.LGarXiv:2608.26733v12026
AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
Che Wang, Jiaming Zhang, Ziqi Zhang +6
cs.CRcs.AIarXiv:2602.20720v12026
AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation
Junchen Ding, Jialiang Dong, Yichen Zhu +5
cs.CRcs.AIarXiv:2608.25667v12026
FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs
Ze Sheng, Aleksandar Kezic, Zhicheng Chen +1
cs.AIcs.CRcs.LGarXiv:2608.25158v12026
Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
Murat Bilgehan Ertan, Marten van Dijk
cs.LGcs.CRarXiv:2601.10237v32026
When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
Yongli Xiang, Zhifang Zhang, Bojun Yang +4
cs.CRcs.CLcs.CYarXiv:2608.03700v12026
Differentially Private Filtering
Jerome Le Ny, George J. Pappas
math.OCcs.CRarXiv:1207.4305v22012
Local Differential Privacy for Deep Learning
M. A. P. Chamikara, P. Bertok, I. Khalil +3
cs.LGcs.CRarXiv:1908.02997v32019
Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences
Yangshijie Zhang
cs.AIcs.CLcs.CRarXiv:2502.17392v12025
A Hybrid Model for Identity Obfuscation by Face Replacement
Qianru Sun, Ayush Tewari, Weipeng Xu +3
cs.CVcs.CRarXiv:1804.04779v22018
LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs
Luis Ibanez-Lissen, Lorena Gonzalez-Manzano, Jose Maria de Fuentes +1
cs.CRcs.AIarXiv:2505.24451v12025
Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT
Antti Koskela, Joonas Jälkö, Lukas Prediger +1
stat.MLcs.CRcs.LGarXiv:2006.07134v32020
Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt
Yupeng Ren, Zhaoxuan Li, Rui Zhang
cs.CRcs.AIarXiv:2609.06226v12026
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Evan Hubinger, Carson Denison, Jesse Mu +36
cs.CRcs.AIcs.CLarXiv:2401.05566v32024
When Agents See Differently: Exposing UI Desynchronization Threats in Mobile Agents
Heng Li, Fulin Zhao, Zhe Geng +3
cs.CRarXiv:2609.16732v12026
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts
Rui Yang, Yang Hong, Yichao Xu +3
cs.AIcs.CRarXiv:2609.00578v12026
TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization
Matan Ben-Tov, Mahmood Sharif
cs.LGcs.CRarXiv:2606.23496v12026
Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic
cs.CRcs.CLcs.SEarXiv:2605.29737v12026
A GAN-Based Framework for Robust DDoS Attack Detection
Makram Chehayeb, Walid Fahs, Amina Rizk +2
cs.LGcs.CRarXiv:2609.18281v12026
SMCC-Empowered Digital Twins for Sensorless Monitoring in Large-Scale AI-Driven IoT Systems
Vincenzo Sammartino
cs.DCcs.CRcs.NIarXiv:2609.09161v12026
A Survey on Machine Learning-based Misbehavior Detection Systems for 5G and Beyond Vehicular Networks
Abdelwahab Boualouache, Thomas Engel
cs.CRcs.LGcs.NIarXiv:2201.10500v12022
Autonomy in Check: Governor-Mediated Adaptive Security at the Edge
Ijaz Ahmad, Ijaz Ahmad, Flavio Esposito +1
cs.CRcs.AIarXiv:2609.18338v12026
PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs
Rushabh Vipulkumar Patel, Dipo Dunsin, Mohammed Almaiah +1
cs.CRcs.AIcs.NIarXiv:2609.18120v12026
Decentralized Trusted Timestamping using the Crypto Currency Bitcoin
Bela Gipp, Norman Meuschke, André Gernandt
cs.CRarXiv:1502.04015v12015
A Survey of Microarchitectural Side-channel Vulnerabilities, Attacks and Defenses in Cryptography
Xiaoxuan Lou, Tianwei Zhang, Jun Jiang +1
cs.CRarXiv:2103.14244v12021
MVD: Memory-Related Vulnerability Detection Based on Flow-Sensitive Graph Neural Networks
Sicong Cao, Xiaobing Sun, Lili Bo +3
cs.CRcs.SEarXiv:2203.02660v12022
Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection
Lijie Zheng, Ji He, Alessandro Brighente +2
cs.CRcs.LGarXiv:2609.16462v12026
Detecting Unknown Encrypted Malicious Traffic in Real Time via Flow Interaction Graph Analysis
Chuanpu Fu, Qi Li, Ke Xu
cs.CRarXiv:2301.13686v12023
GPUThor: Amplifying Rowhammer Attacks via Non-Uniform Patterns to Exploit ECC-Protected GPUs
Chris S. Lin, Joyce Qu, Aditya Rajeev +1
cs.CRarXiv:2609.16546v12026
Instantiating Microcrypt: Obstacles and opportunities via tailored state certification
Jose Carrasco, Jens Eisert, Soumik Ghosh +3
quant-phcs.CRarXiv:2609.15842v12026
BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
Yifei Wang, Dizhan Xue, Shengjie Zhang +1
cs.CLcs.AIcs.CRarXiv:2406.03007v12024
You Shall Not Pass into Ring-0! A User Privacy-Friendly Anti-Cheat Architecture for Personal Computers
Santosh Gokul Narayanan, Giovanni Paladino, Chuqi Zhang +3
cs.CRarXiv:2609.17525v12026
Using Codebooks to Detect Cybercrime Topics in Text Narratives
Shufan Chai, Liangliang Sun, Jessica Staddon
cs.CYcs.CRcs.HCarXiv:2609.16000v12026
InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
Jiachang Zhang, Min Chen, Xiao Ren +4
cs.CRarXiv:2609.16818v12026
MarkSec: Capability-Aware Evaluation of Adversarial Attacks Against LLM Watermarks
Kairong Li, Zhikun Zhang, Xiao Ren +1
cs.CRarXiv:2609.16681v12026
SCHERI: Provably Secure Speculation Under the Constant-Time Policy for CHERI (Extended Version)
Shixin Song, Davide Davoli, Elias Storme +4
cs.CRcs.ARarXiv:2609.17399v12026
SQUIRREL: Testing Database Management Systems with Language Validity and Coverage Feedback
Rui Zhong, Yongheng Chen, Hong Hu +3
cs.CRarXiv:2006.02398v12020
OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design
Jiangrui Yu, Ye Yu, Si Chen +5
cs.ARcs.CRcs.LGarXiv:2609.16898v12026
Stateful Detection of Black-Box Adversarial Attacks
Steven Chen, Nicholas Carlini, David Wagner
cs.CRcs.LGarXiv:1907.05587v12019
ChemMat-AgentSafetyBench: Evaluating Long-Horizon Attacks and Defenses in Chemistry and Materials Agents
Zhan'ao Yao, Zhihao Gao, Liang Yin +9
cs.CRarXiv:2609.11952v12026
Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binaries
Luca Demetrio, Battista Biggio, Giovanni Lagorio +2
cs.CRarXiv:1901.03583v22019
MPCFormer: fast, performant and private Transformer inference with MPC
Dacheng Li, Rulin Shao, Hongyi Wang +3
cs.LGcs.CRarXiv:2211.01452v22022
Hoss: Fast Oblivious Semantic Search with Heterogeneous GPU-CPU-TEE Architecture
Jianzhang Du, Weijie Huang, Chenghong Wang +4
cs.CRarXiv:2609.04522v12026
Cybersecurity in Power Grids: Standards and Research Challenges
Ferran Bohigas-Daranas, Hamid Latif-Martinez, Nicolas Llorens +4
cs.CReess.SYarXiv:2609.16928v12026

Cryptography and Security

Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning

Users really do respond to smishing

The Claws in Plain Sight: Unauthorized Context Disclosure through LLM Agent Tool Calls

The Role of Machine Learning in Cybersecurity

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

DeepInception: Hypnotize Large Language Model to Be Jailbreaker

MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

A Survey on Metaverse: Fundamentals, Security, and Privacy

Red Teaming Language Models with Language Models

Reconstructing Training Data with Informed Adversaries

LLMSec-AV: A Vulnerability Taxonomy and LLM-Driven Software Weakness Discovery Framework for Autonomous Vehicles

SPECTECTOR: Principled Detection of Speculative Information Flows

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Griotte: Verified Compartmentalisation via Capabilities

Casper the Friendly Finality Gadget

Exploiting Per-Core Leakage: Electromagnetic Side-Channel Monitoring of Multicore Architectures

Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation

FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs

Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD

When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills

Differentially Private Filtering

Local Differential Privacy for Deep Learning

Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences

A Hybrid Model for Identity Obfuscation by Face Replacement

LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

When Agents See Differently: Exposing UI Desynchronization Threats in Mobile Agents

Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts

TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs

A GAN-Based Framework for Robust DDoS Attack Detection

SMCC-Empowered Digital Twins for Sensorless Monitoring in Large-Scale AI-Driven IoT Systems

A Survey on Machine Learning-based Misbehavior Detection Systems for 5G and Beyond Vehicular Networks

Autonomy in Check: Governor-Mediated Adaptive Security at the Edge

PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs

Decentralized Trusted Timestamping using the Crypto Currency Bitcoin

A Survey of Microarchitectural Side-channel Vulnerabilities, Attacks and Defenses in Cryptography

MVD: Memory-Related Vulnerability Detection Based on Flow-Sensitive Graph Neural Networks

Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection

Detecting Unknown Encrypted Malicious Traffic in Real Time via Flow Interaction Graph Analysis

GPUThor: Amplifying Rowhammer Attacks via Non-Uniform Patterns to Exploit ECC-Protected GPUs

Instantiating Microcrypt: Obstacles and opportunities via tailored state certification

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

You Shall Not Pass into Ring-0! A User Privacy-Friendly Anti-Cheat Architecture for Personal Computers

Using Codebooks to Detect Cybercrime Topics in Text Narratives

InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation

MarkSec: Capability-Aware Evaluation of Adversarial Attacks Against LLM Watermarks

SCHERI: Provably Secure Speculation Under the Constant-Time Policy for CHERI (Extended Version)

SQUIRREL: Testing Database Management Systems with Language Validity and Coverage Feedback

OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design

Stateful Detection of Black-Box Adversarial Attacks

ChemMat-AgentSafetyBench: Evaluating Long-Horizon Attacks and Defenses in Chemistry and Materials Agents

Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binaries

MPCFormer: fast, performant and private Transformer inference with MPC

Hoss: Fast Oblivious Semantic Search with Heterogeneous GPU-CPU-TEE Architecture

Cybersecurity in Power Grids: Standards and Research Challenges