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 3,900

SurFree: a fast surrogate-free black-box attack
Thibault Maho, Teddy Furon, Erwan Le Merrer
cs.CRcs.AIcs.CVarXiv:2011.12807v12020
AI Deployment Accountability Engineering: A Vision for Accountable AI in Safety-Critical Socio-Technical Systems
Murat Kantarcioglu
cs.AIcs.CRcs.CYarXiv:2609.14592v12026
Everything is a Race and Nakamoto Always Wins
Amir Dembo, Sreeram Kannan, Ertem Nusret Tas +4
cs.CRarXiv:2005.10484v42020
Sample-Preserving Search-to-Decision Reduction for Noisy Linear Equations over Large Moduli
Andrej Bogdanov, Kel Zin Tan, Prashant Nalini Vasudevan
cs.CRarXiv:2610.12913v12026
When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries
Aylin Caliskan, Fabian Yamaguchi, Edwin Dauber +4
cs.CRarXiv:1512.08546v32015
TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOps
Rohit Patel, Susil Kumar Mohanty, Jeenal Chaudhary
cs.DCcs.AIcs.CRarXiv:2609.14762v22026
Cryptanalyzing image encryption using chaotic logistic map
Chengqing Li, Tao Xie, Qi Liu +1
cs.CRarXiv:1301.4089v22013
EviRepair: Evidence-Driven Agents for Reliable Vulnerability Repair
Yilian Shi, Qingyu Liu, Tianyi Zhou +5
cs.CRarXiv:2610.13491v12026
Secrets in Preamble: Practical and Robust PHY Information Hiding for Wi-Fi
Rui Pan, Guanxiong Shen, Linning Peng +2
cs.CReess.SParXiv:2610.13367v12026
Towards Safe World Models: Risks, Defenses, and Evaluation
Xiaoma Wang, Litian Zhang, Xinze Shi +11
cs.CRarXiv:2610.13372v12026
Deployment of a Blockchain-Based Self-Sovereign Identity
Quinten Stokkink, Johan Pouwelse
cs.DCcs.CRcs.CYarXiv:1806.01926v12018
LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse
Boheng Li, Yueming Xing, Yiming Li +2
cs.CVcs.CRarXiv:2610.13333v12026
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
Ziyi Yang, Adel Bibi, Guohao Li +2
cs.CRcs.CLarXiv:2610.13623v12026
Conceptualizing Blockchains: Characteristics & Applications
Karim Sultan, Umar Ruhi, Rubina Lakhani
cs.CYcs.CRarXiv:1806.03693v12018
Safety Graph: When Safety Responses Become Attack Surfaces in Cyber-Physical Systems
Rakesh Podder, Philip D. Hopkins, Sarath Sreedharan +2
cs.CRarXiv:2610.13086v12026
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
Qi Pang, Shengyuan Hu, Wenting Zheng +1
cs.CRcs.CLcs.LGarXiv:2402.16187v32024
DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
Yuheng Tang, Kaijie Zhu, Bonan Ruan +14
cs.SEcs.AIcs.CRarXiv:2601.20882v12026
GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory
Wei Fan, Haoran Li, Zheye Deng +2
cs.CLcs.CRarXiv:2406.11149v22024
LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks
Andreas Happe, Aaron Kaplan, Juergen Cito
cs.CRcs.AIarXiv:2310.11409v72023
Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning
Brian Testa, Yi Xiao, Harshit Sharma +2
cs.LGcs.CRcs.SDarXiv:2211.09273v42022
Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
Shuai Zhao, Meihuizi Jia, Luu Anh Tuan +2
cs.CLcs.AIcs.CRarXiv:2401.05949v62024
HuntGPT: Integrating Machine Learning-Based Anomaly Detection and Explainable AI with Large Language Models (LLMs)
Tarek Ali, Panos Kostakos
cs.CRarXiv:2309.16021v12023
Maximizing Penetration Testing Success with Effective Reconnaissance Techniques using ChatGPT
Sheetal Temara
cs.CRcs.AIarXiv:2307.06391v12023
Multilingual and Multi-Accent Jailbreaking of Audio LLMs
Jaechul Roh, Virat Shejwalkar, Amir Houmansadr
cs.SDcs.AIcs.CLarXiv:2504.01094v12025
Information Design Against Gaming and Learning Adversaries
Madhava Gaikwad
cs.LGcs.AIcs.CRarXiv:2609.31643v12026
A Flash(bot) in the Pan: Measuring Maximal Extractable Value in Private Pools
Ben Weintraub, Christof Ferreira Torres, Cristina Nita-Rotaru +1
cs.CRarXiv:2206.04185v22022
AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents
Xiaoqun Liu, Qiben Yan
cs.CRcs.AIarXiv:2609.14060v12026
MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
Qilin Zhou, Zhengyuan Wei, Haipeng Wang +3
cs.CRcs.AIcs.LGarXiv:2610.10617v12026
A Performance-Sensitive Malware Detection System Using Deep Learning on Mobile Devices
Ruitao Feng, Sen Chen, Xiaofei Xie +3
cs.CRcs.SEarXiv:2005.04970v32020
Lord of the Ring(s): Side Channel Attacks on the CPU On-Chip Ring Interconnect Are Practical
Riccardo Paccagnella, Licheng Luo, Christopher W. Fletcher
cs.CRcs.ARarXiv:2103.03443v12021
Exploring Automated Vulnerability Identification in JavaScript Code Using Large Language Models
Manit Kaushik, Ishir Bhardwaj, Pranav Gupta +2
cs.CRcs.AIarXiv:2609.13816v12026
Mathematics of Isogeny Based Cryptography
Luca De Feo
cs.CRmath.NTarXiv:1711.04062v12017
TyPatch: Transforming Patches into Typestate Rules for Kernel Bug Detection
Ruoyu Wang, Tuo Li, Jia Li
cs.SEcs.AIcs.CRarXiv:2609.13728v12026
Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy
Rui Hu, Yanmin Gong, Yuanxiong Guo
cs.LGcs.CRarXiv:2202.07178v22022
A Survey on Explainable Artificial Intelligence for Cybersecurity
Gaith Rjoub, Jamal Bentahar, Omar Abdel Wahab +5
cs.CRcs.AIcs.NIarXiv:2303.12942v22023
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
Hui Zhang, Yachao Yuan, Jiayun Wang +3
cs.CRcs.AIarXiv:2610.10345v12026
Defensive Sufficiency in a Stackelberg Model of AI Security
Subhabrata Majumdar, Rajlakshmi Chavan
cs.CRcs.AIarXiv:2610.09892v22026
PAST-AI: Physical-layer Authentication of Satellite Transmitters via Deep Learning
Gabriele Oligeri, Simone Raponi, Savio Sciancalepore +1
cs.CRcs.AIcs.CYarXiv:2010.05470v12020
Mitigating Backdoor Attacks in Federated Learning
Chen Wu, Xian Yang, Sencun Zhu +1
cs.CRcs.LGarXiv:2011.01767v22020
Evading Watermark based Detection of AI-Generated Content
Zhengyuan Jiang, Jinghuai Zhang, Neil Zhenqiang Gong
cs.LGcs.CRcs.CVarXiv:2305.03807v52023
Terracotta: Enabling the Adoption of New DRAM Techniques via a Flexible DRAM Interface and Memory Controller
Harsh Songara, Konstantinos Kanellopoulos, F. Nisa Bostancı +6
cs.ARcs.CRcs.DCarXiv:2610.06475v22026
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
When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents
Shuhuai Huang, Jingfeng Zhang, Hong Jia
cs.CRcs.AIarXiv:2609.13889v12026
Flexible Byzantine Fault Tolerance
Dahlia Malkhi, Kartik Nayak, Ling Ren
cs.CRcs.DCarXiv:1904.10067v22019
The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models
Tobias Braun, Jonas Henry Grebe, Emil Sivic +4
cs.CRcs.CVcs.LGarXiv:2610.05453v12026
You Can't See Me: Physical Removal Attacks on LiDAR-based Autonomous Vehicles Driving Frameworks
Yulong Cao, S. Hrushikesh Bhupathiraju, Pirouz Naghavi +3
cs.CRarXiv:2210.09482v22022
Quantum homomorphic encryption for polynomial-sized circuits
Yfke Dulek, Christian Schaffner, Florian Speelman
quant-phcs.CRarXiv:1603.09717v22016
Efficient Secure Federated Learning via Information-Theoretically Secure Key Distribution: A Medical Imaging Case Study
Ivan Donà, Hans H. Brunner, Álvaro Troyano Olivas +3
cs.LGcs.CRarXiv:2610.06420v12026
Explicit Nonlinear Functions beyond the Fourier bound
Swastik Kopparty, Rishabh Kothary, Shanthanu S. Rai
cs.CRcs.CCmath.COarXiv:2610.06362v12026
A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
Fangzhou Wu, Ning Zhang, Somesh Jha +2
cs.CRcs.AIarXiv:2402.18649v12024
Visible-Spectrum Optical Covert Channels in Commodity Smart Lighting
David Noever
cs.CRarXiv:2610.08868v12026
Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents
Nikolaos Kekatos, Dimitrios Nikou, Anastasios Temperekidis +4
cs.CRcs.AIcs.LOarXiv:2610.08928v12026
GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis
Yueqi Xie, Minghong Fang, Renjie Pi +1
cs.CLcs.CRarXiv:2402.13494v22024
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
Wonjun Lee, Kyungsik Yang, Gaeun Ji +5
cs.CRcs.AIcs.CLarXiv:2610.07532v12026
A Three-Axis Stress Test of LLM vs Classical ML for Network Intrusion Detection under Distribution Shift and Adversarial Evasion
Muhammad Ebad Atif, Muhammad Haider Ali
cs.LGcs.AIcs.CRarXiv:2609.13511v12026
Canaries in the Bank: Auditing User-Level Privacy in Private Evolution
Sai Aparna Aketi, Enayat Ullah, Shripad Gade
cs.CRcs.AIcs.LGarXiv:2609.13499v12026
Fuzzing Hardware Like Software
Timothy Trippel, Kang G. Shin, Alex Chernyakhovsky +3
cs.ARcs.CRarXiv:2102.02308v12021
SkillAtlas: An Attack Trace Library for Agent Skills
Yuxin Tian, Zenghao Duan, Liang Pang +2
cs.CRcs.AIarXiv:2609.13353v32026
Cryptographic security of quantum key distribution
Christopher Portmann, Renato Renner
quant-phcs.CRcs.ITarXiv:1409.3525v12014
Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use
Shang Wang, Tianqing Zhu, Huajie Chen +3
cs.CRcs.AIarXiv:2610.04985v12026

Cryptography and Security

SurFree: a fast surrogate-free black-box attack

AI Deployment Accountability Engineering: A Vision for Accountable AI in Safety-Critical Socio-Technical Systems

Everything is a Race and Nakamoto Always Wins

Sample-Preserving Search-to-Decision Reduction for Noisy Linear Equations over Large Moduli

When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries

TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOps

Cryptanalyzing image encryption using chaotic logistic map

EviRepair: Evidence-Driven Agents for Reliable Vulnerability Repair

Secrets in Preamble: Practical and Robust PHY Information Hiding for Wi-Fi

Towards Safe World Models: Risks, Defenses, and Evaluation

Deployment of a Blockchain-Based Self-Sovereign Identity

LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse

APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

Conceptualizing Blockchains: Characteristics & Applications

Safety Graph: When Safety Responses Become Attack Surfaces in Cyber-Physical Systems

No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices

DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle

GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory

LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks

Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning

Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning

HuntGPT: Integrating Machine Learning-Based Anomaly Detection and Explainable AI with Large Language Models (LLMs)

Maximizing Penetration Testing Success with Effective Reconnaissance Techniques using ChatGPT

Multilingual and Multi-Accent Jailbreaking of Audio LLMs

Information Design Against Gaming and Learning Adversaries

A Flash(bot) in the Pan: Measuring Maximal Extractable Value in Private Pools

AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents

MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking

A Performance-Sensitive Malware Detection System Using Deep Learning on Mobile Devices

Lord of the Ring(s): Side Channel Attacks on the CPU On-Chip Ring Interconnect Are Practical

Exploring Automated Vulnerability Identification in JavaScript Code Using Large Language Models

Mathematics of Isogeny Based Cryptography

TyPatch: Transforming Patches into Typestate Rules for Kernel Bug Detection

Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy

A Survey on Explainable Artificial Intelligence for Cybersecurity

SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing

Defensive Sufficiency in a Stackelberg Model of AI Security

PAST-AI: Physical-layer Authentication of Satellite Transmitters via Deep Learning

Mitigating Backdoor Attacks in Federated Learning

Evading Watermark based Detection of AI-Generated Content

Terracotta: Enabling the Adoption of New DRAM Techniques via a Flexible DRAM Interface and Memory Controller

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

When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents

Flexible Byzantine Fault Tolerance

The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models

You Can't See Me: Physical Removal Attacks on LiDAR-based Autonomous Vehicles Driving Frameworks

Quantum homomorphic encryption for polynomial-sized circuits

Efficient Secure Federated Learning via Information-Theoretically Secure Key Distribution: A Medical Imaging Case Study

Explicit Nonlinear Functions beyond the Fourier bound

A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems

Visible-Spectrum Optical Covert Channels in Commodity Smart Lighting

Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents

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

Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge

A Three-Axis Stress Test of LLM vs Classical ML for Network Intrusion Detection under Distribution Shift and Adversarial Evasion

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

Fuzzing Hardware Like Software

SkillAtlas: An Attack Trace Library for Agent Skills

Cryptographic security of quantum key distribution

Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use