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)

3,241 to 3,300 of 4,520

On the Security Vulnerabilities of Text-to-SQL Models
Xutan Peng, Yipeng Zhang, Jingfeng Yang +1
cs.CLcs.CRcs.DBarXiv:2211.15363v42022
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
Zeyu Qin, Yanbo Fan, Yi Liu +4
cs.CVcs.CRcs.LGarXiv:2210.05968v12022
ExplainGuard: A Zero Trust Framework for Post-Hoc Explanation Integrity Guarantees in Blackbox XAI Models
Maraz Mia, Shovan Roy, Mir Mehedi A. Pritom +1
cs.CRcs.AIarXiv:2608.21803v12026
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
Wieland Brendel, Jonas Rauber, Matthias Bethge
stat.MLcs.CRcs.CVarXiv:1712.04248v22017
The Anonymity Gap: Understanding Real Privacy in Shielded UTXO-based Protocols for DeFi
Hanze Guo, Stefanos Chaliasos, Yebo Feng +1
cs.CRarXiv:2608.22987v12026
LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks
Saad Ullah, Mingji Han, Saurabh Pujar +3
cs.CRarXiv:2312.12575v32023
Poster: FedWM-Guard: Thwarting Imagination Poisoning in Federated World Model-based Autonomous Driving
Sheng Liu, Panos Papadimitratos
cs.CRarXiv:2609.29178v12026
On the Exploitability of Instruction Tuning
Manli Shu, Jiongxiao Wang, Chen Zhu +3
cs.CRcs.CLcs.LGarXiv:2306.17194v22023
Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts
Leyang Li, Shilin Lu, Yan Ren +1
cs.CVcs.AIcs.CRarXiv:2504.12782v12025
The Capacity of Private Information Retrieval
Hua Sun, Syed A. Jafar
cs.ITcs.CRcs.IRarXiv:1602.09134v22016
CrypTFlow: Secure TensorFlow Inference
Nishant Kumar, Mayank Rathee, Nishanth Chandran +3
cs.CRcs.LGcs.PLarXiv:1909.07814v22019
Structured Driving-State Narratives for Small Language Model-Based GNSS Spoofing Detection
Abyad Enan, Sagar Dasgupta, Mizanur Rahman +1
cs.CRcs.AIarXiv:2608.17092v12026
The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems
Yue Xing, Pengfei He, Zitao Li
cs.CRcs.AIcs.LGarXiv:2609.27155v12026
Can Tainted Pixels Expose Deepfake Videos?
Juan Hu, Shaojing Fan, Sanjay Saha +2
cs.CRcs.CVarXiv:2608.27492v12026
On the Effectiveness of Kernel-Level Evidence for Agent Security
Spencer King, Zhilu Zhang, Mikhail Kuznetsov +3
cs.CRcs.AIarXiv:2609.28915v12026
Blockchain-based Digital Twins: Research Trends, Issues, and Future Challenges
Sabah Suhail, Rasheed Hussain, Raja Jurdak +4
cs.CRarXiv:2103.11585v22021
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
Bypassing the Safety Training of Open-Source LLMs with Priming Attacks
Jason Vega, Isha Chaudhary, Changming Xu +1
cs.CRcs.AIcs.CLarXiv:2312.12321v22023
Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks
Octavian Suciu, Radu Mărginean, Yiğitcan Kaya +2
cs.CRcs.LGarXiv:1803.06975v22018
What's Your NIC Whispering? Network Threat Behavior Recognition via NIC Electromagnetic Side-Channel Leakage
Hongchao Wang, Linrui Li, Yunkai Zou +5
cs.CRcs.ARarXiv:2608.22941v12026
CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering
Mark Russinovich
cs.CRcs.AIarXiv:2609.36570v12026
nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data
Fabian Boemer, Yixing Lao, Rosario Cammarota +1
cs.CRarXiv:1810.10121v32018
Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling
Stefano Leggio, Giulio Rossolini, Alessandro Biondi
cs.CRcs.AIarXiv:2609.01232v12026
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Briland Hitaj, Giuseppe Ateniese, Fernando Perez-Cruz
cs.CRcs.LGstat.MLarXiv:1702.07464v32017
ThreatLens: Evidence-Guided Ranking of High-Priority CVEs
Soroush Motamedi Sedeh, Panteha Shahrivar, Malaika Qureshi +2
cs.CRarXiv:2608.22306v12026
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
Avi Schwarzschild, Micah Goldblum, Arjun Gupta +2
cs.LGcs.CRcs.CVarXiv:2006.12557v32020
On the Learnability of Watermarks for Language Models
Chenchen Gu, Xiang Lisa Li, Percy Liang +1
cs.LGcs.CLcs.CRarXiv:2312.04469v32023
Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning
Hamza Harkous, Kassem Fawaz, Rémi Lebret +3
cs.CLcs.CRcs.HCarXiv:1802.02561v22018
Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense
Fernando Martinez, Abhishek Satyam, Tao Li +3
cs.CRcs.LGarXiv:2610.09337v12026
Large-scale online deanonymization with LLMs
Simon Lermen, Daniel Paleka, Joshua Swanson +3
cs.CRcs.AIcs.LGarXiv:2602.16800v22026
A Survey on Data-driven Software Vulnerability Assessment and Prioritization
Triet H. M. Le, Huaming Chen, M. Ali Babar
cs.SEcs.AIcs.CRarXiv:2107.08364v42021
AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks
Jiacen Xu, Jack W. Stokes, Geoff McDonald +5
cs.CRcs.AIarXiv:2403.01038v12024
Lightweight Detection of Electromagnetic Signal Injection Attacks on Image Sensors
Youqian Zhang, Chunxi Yang, Eugene Yujun Fu +3
cs.CRarXiv:2609.06973v12026
DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks
Yupei Liu, Yuqi Jia, Jinyuan Jia +2
cs.CRcs.AIarXiv:2504.11358v42025
A Survey of Stealth Malware: Attacks, Mitigation Measures, and Steps Toward Autonomous Open World Solutions
Ethan M. Rudd, Andras Rozsa, Manuel Günther +1
cs.CRcs.CVarXiv:1603.06028v22016
Enterprise-Grade Security for the Model Context Protocol (MCP): Frameworks and Mitigation Strategies
Vineeth Sai Narajala, Idan Habler
cs.CRcs.AIarXiv:2504.08623v22025
A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures
Dezhang Kong, Shi Lin, Zhenhua Xu +16
cs.CRarXiv:2506.19676v42025
Effective Interventions Against AI-Enhanced Scams
Kyle Fredrickson
cs.CRcs.CYarXiv:2609.00806v12026
ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
Junichi Yamagishi, Xin Wang, Massimiliano Todisco +8
eess.AScs.CRcs.LGarXiv:2109.00537v12021
When Measurement Constraints Favor Quantum Computational Sensing for Stealthy Power-Grid Attack Detection
Saisubramaniam Gopalakrishnan, Supreeth B S, Pranav Sarda +2
quant-phcs.CRarXiv:2609.10606v12026
Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents
Jinqian Zhang, Haojun Xia, Shujiang Wu +4
cs.CRcs.AIarXiv:2609.28585v12026
AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems
Basavesh Ammanaghatta Shivakumar, Swarn Priya, Peng Gao
cs.CRarXiv:2608.22868v12026
No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models
Shengyao Zhang, Mi Zhang, Xudong Pan +1
cs.CRcs.CLarXiv:2312.09494v22023
Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregation
Miguel Morona-Mínguez, Fernando Pérez-González, Alberto Pedrouzo-Ulloa
cs.CRcs.LGarXiv:2609.01945v12026
Keeping Authorities "Honest or Bust" with Decentralized Witness Cosigning
Ewa Syta, Iulia Tamas, Dylan Visher +6
cs.CRarXiv:1503.08768v42015
Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents
Jun He, Deying Yu
cs.CRarXiv:2609.02127v12026
Practical and Private (Deep) Learning without Sampling or Shuffling
Peter Kairouz, Brendan McMahan, Shuang Song +3
cs.CRcs.LGarXiv:2103.00039v32021
Low-Cost High-Power Membership Inference Attacks
Sajjad Zarifzadeh, Philippe Liu, Reza Shokri
stat.MLcs.CRcs.LGarXiv:2312.03262v32023
TANGO: Watermarking Masked Diffusion Language Models in Token Pairs
Kasra Arabi, Nir Weinberger, Micah Goldblum +1
cs.LGcs.CLcs.CRarXiv:2609.35224v12026
LLMscope: Extracting LLM Assets from Edge AI Chips via Optical Probing
Dev Mehta, Lily Dukette, William Folan +4
cs.CRcs.AIarXiv:2608.25321v12026
Sigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering
Kemal Davaslioglu, Sastry Kompella
cs.AIcs.CRarXiv:2610.09007v12026
Seeing is Not Believing: Breaking the Physical-to-Digital Trust Boundary in Robotics
Leming Shen, Shikai Geng, Yuanqing Zheng +1
cs.ROcs.CRarXiv:2609.08280v12026
Privacy for Free: How does Dataset Condensation Help Privacy?
Tian Dong, Bo Zhao, Lingjuan Lyu
cs.CRcs.LGarXiv:2206.00240v12022
LLM Anonymization Against Agentic Re-Identification
Ziwen Li, Jianing Wen, Tianshi Li
cs.CRcs.CLarXiv:2605.30848v22026
Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
Xander Davies, Eric Winsor, Alexandra Souly +4
cs.LGcs.CRarXiv:2502.14828v22025
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents
Xinjie Shen, Junran Wang, Rongzhe Wei +1
cs.CRcs.AIarXiv:2609.34518v12026
One Node, Two Roles: Simultaneous Contests for Validation and Attention in Rollups
Pranay Anchuri, Ben Berger, Matteo Campanelli +1
cs.CRarXiv:2610.12220v12026
Federated Neural Collaborative Filtering
Vasileios Perifanis, Pavlos S. Efraimidis
cs.IRcs.CRcs.LGarXiv:2106.04405v22021
Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks
Guy Frankovits, Lior Yasur, Fred M. Grabovski +1
cs.CRcs.AIarXiv:2609.11404v12026
Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence
Peng Gao, Fei Shao, Xiaoyuan Liu +6
cs.CRcs.CLcs.DBarXiv:2010.13637v22020

Cryptography and Security

On the Security Vulnerabilities of Text-to-SQL Models

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation

ExplainGuard: A Zero Trust Framework for Post-Hoc Explanation Integrity Guarantees in Blackbox XAI Models

Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

The Anonymity Gap: Understanding Real Privacy in Shielded UTXO-based Protocols for DeFi

LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks

Poster: FedWM-Guard: Thwarting Imagination Poisoning in Federated World Model-based Autonomous Driving

On the Exploitability of Instruction Tuning

Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts

The Capacity of Private Information Retrieval

CrypTFlow: Secure TensorFlow Inference

Structured Driving-State Narratives for Small Language Model-Based GNSS Spoofing Detection

The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems

Can Tainted Pixels Expose Deepfake Videos?

On the Effectiveness of Kernel-Level Evidence for Agent Security

Blockchain-based Digital Twins: Research Trends, Issues, and Future Challenges

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

Bypassing the Safety Training of Open-Source LLMs with Priming Attacks

Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks

What's Your NIC Whispering? Network Threat Behavior Recognition via NIC Electromagnetic Side-Channel Leakage

CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering

nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data

Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling

Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning

ThreatLens: Evidence-Guided Ranking of High-Priority CVEs

Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks

On the Learnability of Watermarks for Language Models

Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning

Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense

Large-scale online deanonymization with LLMs

A Survey on Data-driven Software Vulnerability Assessment and Prioritization

AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks

Lightweight Detection of Electromagnetic Signal Injection Attacks on Image Sensors

DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks

A Survey of Stealth Malware: Attacks, Mitigation Measures, and Steps Toward Autonomous Open World Solutions

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

A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures

Effective Interventions Against AI-Enhanced Scams

ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection

When Measurement Constraints Favor Quantum Computational Sensing for Stealthy Power-Grid Attack Detection

Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents

AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems

No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models

Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregation

Keeping Authorities "Honest or Bust" with Decentralized Witness Cosigning

Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents

Practical and Private (Deep) Learning without Sampling or Shuffling

Low-Cost High-Power Membership Inference Attacks

TANGO: Watermarking Masked Diffusion Language Models in Token Pairs

LLMscope: Extracting LLM Assets from Edge AI Chips via Optical Probing

Sigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering

Seeing is Not Believing: Breaking the Physical-to-Digital Trust Boundary in Robotics

Privacy for Free: How does Dataset Condensation Help Privacy?

LLM Anonymization Against Agentic Re-Identification

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs

SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents

One Node, Two Roles: Simultaneous Contests for Validation and Attention in Rollups

Federated Neural Collaborative Filtering

Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks

Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence