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)

3,421 to 3,480 of 4,566

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
Lei Hsiung, Tianyu Pang, Yung-Chen Tang +4
cs.CRcs.CLcs.LGarXiv:2506.05346v12025
Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
Madhura Joshi, Ankit Pal, Malaikannan Sankarasubbu
cs.LGcs.AIcs.CRarXiv:2211.07893v22022
SwarmSense-DNN: A Trustworthy and Decentralized Neural Framework for Proactive Anomaly Defense in Consumer IoT
Jing Yang, Vijay Govindarajan, Saad Arif +6
cs.CRcs.NIarXiv:2606.11803v12026
The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
Feng He, Tianqing Zhu, Dayong Ye +3
cs.CRarXiv:2407.19354v22024
Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control
Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula +4
cs.CRcs.AIarXiv:2609.14003v12026
VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
Junda Lin, Zhaomeng Zhou, Zhi Zheng +4
cs.CRcs.AIarXiv:2601.05755v22026
The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices
Wanlun Ma, Derui Wang, Ruoxi Sun +3
cs.CRcs.AIarXiv:2209.11715v32022
Canaries in the Bank: Auditing User-Level Privacy in Private Evolution
Sai Aparna Aketi, Enayat Ullah, Shripad Gade
cs.CRcs.AIcs.LGarXiv:2609.13499v12026
Quantum Key Distribution with Classical Bob
Michel Boyer, Dan Kenigsberg, Tal Mor
quant-phcs.CRarXiv:quant-ph/0703107v12007
Dynamic Risk Assessments for Offensive Cybersecurity Agents
Boyi Wei, Benedikt Stroebl, Jiacen Xu +3
cs.CRcs.AIarXiv:2505.18384v52025
Using quantum key distribution for cryptographic purposes: a survey
Romain Alléaume, Cyril Branciard, Jan Bouda +20
quant-phcs.CRcs.ITarXiv:quant-ph/0701168v32007
Coverage Is Not Containment: A Fundamental Limit of Admission-Time Defenses Against Coordinated Poisoning of Vector Retrieval
Prashant Kumar Pathak, Tarun Kumar Sharma
cs.CRcs.CLcs.IRarXiv:2608.16044v12026
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
Pin-Yu Chen, Yash Sharma, Huan Zhang +2
stat.MLcs.CRcs.LGarXiv:1709.04114v32017
Silent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems
Doniyorkhon Obidov, Shivayogi Akki, Tan Chen +1
cs.ROcs.AIcs.CRarXiv:2609.26184v12026
Local Sensitivity in Exponential Selection: Failure Modes and Valid Calibrations
Dung Nguyen, Anil Vullikanti
cs.DScs.CRarXiv:2610.11870v12026
SkillAtlas: An Attack Trace Library for Agent Skills
Yuxin Tian, Zenghao Duan, Liang Pang +2
cs.CRcs.AIarXiv:2609.13353v32026
"They don't care about this": A Systematic Study of TEE Build Reproducibility in the Wild
Annika Wilde, Marco Gutfleisch, Felix Reichmann +4
cs.CRarXiv:2609.11411v12026
Beyond the Prank: The Hidden Expertise of TSS Scambaiters
Saleh Alsyefi, Anish Chand, Matthew Edwards +1
cs.CRcs.CYarXiv:2609.06103v12026
The Uncontrolled Variable: Vision-Language Model Refusal Responds to Image Presence in Ways Risk Cannot Explain
Haoyu Zhang, Yi Feng, Shibo Zheng +6
cs.CRcs.AIarXiv:2609.26174v12026
Differentially Private Mixing of Public Datasets Improves Private Learning
Yufei Chen, Tejumade Afonja, Anvith Thudi +1
cs.LGcs.AIcs.CRarXiv:2610.06636v12026
DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems
Lei Ma, Felix Juefei-Xu, Fuyuan Zhang +9
cs.SEcs.CRcs.LGarXiv:1803.07519v42018
Minutiae Extraction from Fingerprint Images - a Review
Roli Bansal, Priti Sehgal, Punam Bedi
cs.CVcs.CRarXiv:1201.1422v12011
ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control
Xukun Luan, Zhongxiang Lei, Chen Gong +3
cs.ROcs.CRcs.LGarXiv:2609.28378v12026
A Systematization of Knowledge on DeFi Vaults: Architectures, Curation Mechanisms, and Strategy Design
Davide Mancino, Luca Pennella
cs.CRcs.CEcs.CYarXiv:2610.01300v12026
Shuffling is Not Enough: Breaking Permutation-Based Model Confidentiality in Hybrid FHE Inference
Jiseung Kim, Hyung Tae Lee
cs.CRarXiv:2609.12911v12026
Can AI Oversight Be Zero Knowledge?
Alessandro Chiesa, Ziyi Guan, Burcu Yildiz
cs.AIcs.CCcs.CRarXiv:2610.01995v12026
A Graph-Based Approach for Mapping Kernel-Level Telemetry to MITRE ATT&CK
Matteo Lupinacci, Luigi Arena, Francesco Blefari +1
cs.CRcs.AIarXiv:2609.12841v12026
Multiple Purposes, Multiple Problems: A User Study of Consent Dialogs after GDPR
Dominique Machuletz, Rainer Böhme
cs.HCcs.CRcs.CYarXiv:1908.10048v22019
PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
Runpeng Geng, Yanting Wang, Chenlong Yin +3
cs.CRcs.AIcs.CLarXiv:2511.10720v12025
AI Models Can Provably Hide Arbitrary Capabilities
Andis Draguns, Sumeet Ramesh Motwani, Raymond Douglas +1
cs.LGcs.CRarXiv:2610.13928v12026
RobResilience: Implementing and Evaluating a Resilience Framework for Cyber-Physical Embodied Systems
Gysella Imrell, Emanuele Miotto, Mahya Mohammadi Kashani +2
cs.CRcs.ROeess.SYarXiv:2609.17349v12026
Disentangling Adversarial Robustness and Generalization
David Stutz, Matthias Hein, Bernt Schiele
cs.CVcs.CRcs.LGarXiv:1812.00740v22018
Encrypted DNS --> Privacy? A Traffic Analysis Perspective
Sandra Siby, Marc Juarez, Claudia Diaz +2
cs.CRarXiv:1906.09682v32019
Do Users Write More Insecure Code with AI Assistants?
Neil Perry, Megha Srivastava, Deepak Kumar +1
cs.CRarXiv:2211.03622v32022
ToolTweak: An Attack on Tool Selection in LLM-based Agents
Jonathan Sneh, Ruomei Yan, Jialin Yu +6
cs.CRcs.AIarXiv:2510.02554v12025
Evaluating Explanation Methods for Deep Learning in Security
Alexander Warnecke, Daniel Arp, Christian Wressnegger +1
cs.LGcs.CRstat.MLarXiv:1906.02108v42019
Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
Tong Liu, Yingjie Zhang, Zhe Zhao +3
cs.CRcs.AIarXiv:2402.18104v22024
Mitigating Error Propagation in Chain-of-Thought: A Tree-of-Thought Framework for Smart Contract Repair
Jingping Zhu, Hongping Wang, Xiaoqi Li
cs.CRcs.SEarXiv:2608.22345v12026
Metamorphism: A mathematical challenge for antivirus technology
Luis M. Augusto
cs.CRarXiv:2608.27007v12026
ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning
Bingchen Pei, Lichong Chen, Bingxi Zhao +8
cs.CRcs.AIcs.CLarXiv:2610.01184v12026
The Evolution of Binary Decompilation in the Modern Era: A Taxonomy, Literature Review, and Future Perspectives
Omar Abusabha, Sungjae Hwang
cs.SEcs.CRarXiv:2608.24955v12026
ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection
Xinhang Ma, Chaowei Xiao, William Yeoh +2
cs.CRarXiv:2608.27496v12026
Discharged Payment Channels: Quantifying the Lightning Network's Resilience to Topology-Based Attacks
Elias Rohrer, Julian Malliaris, Florian Tschorsch
cs.NIcs.CRcs.SIarXiv:1904.10253v12019
Search Me If You Can: Privacy-preserving Location Query Service
Xiang-Yang Li, Taeho Jung
cs.CRcs.SIarXiv:1208.0107v32012
ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus
Li Zeng, Mingcheng Duan, Longfei Fan +5
cs.CVcs.CRarXiv:2609.28239v12026
DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents
Shiyi Yang, Zhibo Hu, Xinshu Li +5
cs.CRcs.CLcs.IRarXiv:2503.23804v32025
A Survey on Trust Metrics for Autonomous Robotic Systems
Vincenzo DiLuoffo, William R. Michalson
cs.ROcs.CRarXiv:2106.15015v22021
Plug-in privacy for Smart Metering billing
Marek Jawurek, Martin Johns, Florian Kerschbaum
cs.CRarXiv:1012.2248v22010
Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimation
John C. Duchi, Michael I. Jordan, Martin J. Wainwright
math.STcs.CRcs.ITarXiv:1305.6000v12013
IDORacle: Template-Guided SQL-Sink Mediation for Object-Level Authorization in Java Applications
Yuewantong Song, Guanhang Shi, Yin Cai +5
cs.CRarXiv:2609.12426v12026
Why User Studies and Participant Experience Reporting Matter for VR Motion Privacy?
Azim Ibragimov, Eric D. Ragan
cs.HCcs.CRarXiv:2609.12415v12026
Blockchain and AI-based Solutions to Combat Coronavirus (COVID-19)-like Epidemics: A Survey
Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana +1
cs.CReess.SParXiv:2106.14631v12021
A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos
Yang Yao, Xuan Tong, Ruofan Wang +5
cs.CRcs.AIcs.CLarXiv:2502.15806v22025
On the Feasibility of CubeSats Application Sandboxing for Space Missions
Gabriele Marra, Ulysse Planta, Philipp Wüstenberg +1
cs.CRarXiv:2404.04127v12024
SoK: Are LLMs Reliable at Source Code Recovery? A Taxonomy and Empirical Evaluation
Varun Kohli, Lee Bing Cheng, Nur Hazim Ghazali +3
cs.CRcs.SEarXiv:2610.11556v12026
GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis
Yueqi Xie, Minghong Fang, Renjie Pi +1
cs.CLcs.CRarXiv:2402.13494v22024
E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT
Wai Weng Lo, Siamak Layeghy, Mohanad Sarhan +2
cs.NIcs.AIcs.CRarXiv:2103.16329v82021
$Z^2$-ACT: End-to-End Verifiable Agentic Intent Control for Open 6G RAN
Sunder Ali Khowaja, Kapal Dev, George C. Alexandropoulos
cs.CRcs.AIcs.NIarXiv:2608.21049v12026
Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
Xinyi Hou, Yanjie Zhao, Shenao Wang +1
cs.CRcs.AIarXiv:2503.23278v22025
Function Name Is All You Need to Detect Blockchain Application Attacks
Rui Xi, Zehua Wang, Karthik Pattabiraman
cs.CRarXiv:2609.12315v12026

Cryptography and Security

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets

Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges

SwarmSense-DNN: A Trustworthy and Decentralized Neural Framework for Proactive Anomaly Defense in Consumer IoT

The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies

Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit

The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices

Canaries in the Bank: Auditing User-Level Privacy in Private Evolution

Quantum Key Distribution with Classical Bob

Dynamic Risk Assessments for Offensive Cybersecurity Agents

Using quantum key distribution for cryptographic purposes: a survey

Coverage Is Not Containment: A Fundamental Limit of Admission-Time Defenses Against Coordinated Poisoning of Vector Retrieval

EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples

Silent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems

Local Sensitivity in Exponential Selection: Failure Modes and Valid Calibrations

SkillAtlas: An Attack Trace Library for Agent Skills

"They don't care about this": A Systematic Study of TEE Build Reproducibility in the Wild

Beyond the Prank: The Hidden Expertise of TSS Scambaiters

The Uncontrolled Variable: Vision-Language Model Refusal Responds to Image Presence in Ways Risk Cannot Explain

Differentially Private Mixing of Public Datasets Improves Private Learning

DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems

Minutiae Extraction from Fingerprint Images - a Review

ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control

A Systematization of Knowledge on DeFi Vaults: Architectures, Curation Mechanisms, and Strategy Design

Shuffling is Not Enough: Breaking Permutation-Based Model Confidentiality in Hybrid FHE Inference

Can AI Oversight Be Zero Knowledge?

A Graph-Based Approach for Mapping Kernel-Level Telemetry to MITRE ATT&CK

Multiple Purposes, Multiple Problems: A User Study of Consent Dialogs after GDPR

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization

AI Models Can Provably Hide Arbitrary Capabilities

RobResilience: Implementing and Evaluating a Resilience Framework for Cyber-Physical Embodied Systems

Disentangling Adversarial Robustness and Generalization

Encrypted DNS --> Privacy? A Traffic Analysis Perspective

Do Users Write More Insecure Code with AI Assistants?

ToolTweak: An Attack on Tool Selection in LLM-based Agents

Evaluating Explanation Methods for Deep Learning in Security

Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction

Mitigating Error Propagation in Chain-of-Thought: A Tree-of-Thought Framework for Smart Contract Repair

Metamorphism: A mathematical challenge for antivirus technology

ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning

The Evolution of Binary Decompilation in the Modern Era: A Taxonomy, Literature Review, and Future Perspectives

ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection

Discharged Payment Channels: Quantifying the Lightning Network's Resilience to Topology-Based Attacks

Search Me If You Can: Privacy-preserving Location Query Service

ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus

DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents

A Survey on Trust Metrics for Autonomous Robotic Systems

Plug-in privacy for Smart Metering billing

Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimation

IDORacle: Template-Guided SQL-Sink Mediation for Object-Level Authorization in Java Applications

Why User Studies and Participant Experience Reporting Matter for VR Motion Privacy?

Blockchain and AI-based Solutions to Combat Coronavirus (COVID-19)-like Epidemics: A Survey

A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos

On the Feasibility of CubeSats Application Sandboxing for Space Missions

SoK: Are LLMs Reliable at Source Code Recovery? A Taxonomy and Empirical Evaluation

GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis

E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT

$Z^2$-ACT: End-to-End Verifiable Agentic Intent Control for Open 6G RAN

Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions

Function Name Is All You Need to Detect Blockchain Application Attacks