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)

1,021 to 1,080 of 2,547

Privacy Amplification Without Independence: How Far Negative Dependence Carries the Guarantees of Poisson Subsampling
Xujun Che, Depeng Xu
cs.CRarXiv:2609.01944v12026
Adversarial camera stickers: A physical camera-based attack on deep learning systems
Juncheng Li, Frank R. Schmidt, J. Zico Kolter
cs.CVcs.CRcs.LGarXiv:1904.00759v42019
IoTSense: Behavioral Fingerprinting of IoT Devices
Bruhadeshwar Bezawada, Maalvika Bachani, Jordan Peterson +3
cs.CRarXiv:1804.03852v12018
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
Steffen Eger, Gözde Gül Şahin, Andreas Rücklé +6
cs.CLcs.CRcs.CVarXiv:1903.11508v22019
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Mrinank Sharma, Meg Tong, Jesse Mu +40
cs.CLcs.AIcs.CRarXiv:2501.18837v12025
A Scenario-Based Evaluation of CRQC+AI Vulnerability Spectrum for TLS 1.3 Cryptographic Dependencies
Noel Grover, Mussie Haile, Brad Pedersen +2
cs.CRarXiv:2608.23785v12026
Summaries:한국어 日本語简体中文
Interpretable Deep Learning under Fire
Xinyang Zhang, Ningfei Wang, Hua Shen +3
cs.CRcs.LGarXiv:1812.00891v32018
NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing
Padmeswari Nandiya, Ahmad Mohsin, Ahmed Ibrahim +2
cs.CRcs.IRarXiv:2609.00604v12026
Context Inference Attacks Without Jailbreaks
Prince Jha, Samuele Poppi, Nils Lukas
cs.CRcs.LGarXiv:2609.01663v12026
Explainable Adaptive Zero Trust Framework for AWS with Adversarial Robustness Evaluation
Om Singh, Yagyaraj Pandey, Nandini Pathak
cs.CRcs.CYcs.LGarXiv:2608.21477v12026
Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making
Pasquale Malacaria, Yunxiao Zhang
cs.CRcs.AIarXiv:2608.20966v12026
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi +1
cs.CRcs.LGarXiv:2602.20156v32026
If It Walks Like an Arbitrage: Protocol-Agnostic Detection with Decidable Structural Equivalence
Adam Khayam, Hamid Kolli, Mohamed Iguernalala +1
q-fin.CPcs.CRcs.LGarXiv:2608.20377v12026
Influence of Logging Frameworks on Bind9
Max Schrötter, Hannes Signer, Bettina Schnor
cs.CRcs.NIcs.OSarXiv:2609.00954v12026
ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents
Yutao Mou, Pengfei Yang, Zhe Yin +6
cs.CRcs.CLarXiv:2608.11878v12026
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling
Vitaly Feldman, Audra McMillan, Kunal Talwar
cs.LGcs.CRcs.DSarXiv:2012.12803v32020
Generative Adversarial Networks: A Survey Towards Private and Secure Applications
Zhipeng Cai, Zuobin Xiong, Honghui Xu +3
cs.LGcs.CRarXiv:2106.03785v12021
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
Natalia Ponomareva, Hussein Hazimeh, Alex Kurakin +6
cs.LGcs.CRstat.MLarXiv:2303.00654v32023
Detection of False Data Injection Attacks in Smart Grid: A Secure Federated Deep Learning Approach
Yang Li, Xinhao Wei, Yuanzheng Li +2
cs.CReess.SYarXiv:2209.00778v22022
IBM Federated Learning: an Enterprise Framework White Paper V0.1
Heiko Ludwig, Nathalie Baracaldo, Gegi Thomas +21
cs.LGcs.CRcs.DCarXiv:2007.10987v12020
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
Jan Betley, Daniel Tan, Niels Warncke +5
cs.CLcs.AIcs.CRarXiv:2502.17424v72025
threaTrace: Detecting and Tracing Host-based Threats in Node Level Through Provenance Graph Learning
Su Wang, Zhiliang Wang, Tao Zhou +6
cs.CRcs.LGarXiv:2111.04333v12021
Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion
Phong Trinh Duy, Trang Dang Yen, Hung Nguyen-Huu +5
cs.SEcs.AIcs.CRarXiv:2609.01187v12026
SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
Yanna Jiang, Delong Li, Haiyu Deng +4
cs.CRcs.AIcs.CEarXiv:2602.20867v12026
nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data
Fabian Boemer, Anamaria Costache, Rosario Cammarota +1
cs.CRarXiv:1908.04172v22019
Do you need a blockchain in construction? Use case categories and decision framework for DLT design options
Jens J. Hunhevicz, Daniel M. Hall
cs.CRarXiv:2004.04626v12020
Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning
Jinhyun So, Basak Guler, A. Salman Avestimehr
cs.LGcs.CRcs.DCarXiv:2002.04156v32020
Machine Learning Based Network Vulnerability Analysis of Industrial Internet of Things
Maede Zolanvari, Marcio A. Teixeira, Lav Gupta +2
cs.CRcs.LGcs.NIarXiv:1911.05771v12019
HEAX: An Architecture for Computing on Encrypted Data
M. Sadegh Riazi, Kim Laine, Blake Pelton +1
cs.CRcs.AIcs.ARarXiv:1909.09731v22019
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
Hadi Salman, Greg Yang, Jerry Li +4
cs.LGcs.CRstat.MLarXiv:1906.04584v52019
Performance Comparison of Intrusion Detection Systems and Application of Machine Learning to Snort System
Syed Ali Raza Shah, Biju Issac
cs.NIcs.CRcs.LGarXiv:1710.04843v22017
A new Backdoor Attack in CNNs by training set corruption without label poisoning
Mauro Barni, Kassem Kallas, Benedetta Tondi
cs.CRcs.CVcs.LGarXiv:1902.11237v12019
Decentralized Applications: The Blockchain-Empowered Software System
Wei Cai, Zehua Wang, Jason B. Ernst +3
cs.DCcs.CRcs.CYarXiv:1810.05365v12018
Federated Quantum Machine Learning
Samuel Yen-Chi Chen, Shinjae Yoo
quant-phcs.AIcs.CRarXiv:2103.12010v12021
Exploring Connections Between Active Learning and Model Extraction
Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli +2
cs.LGcs.CRstat.MLarXiv:1811.02054v62018
SoK: Sanitizing for Security
Dokyung Song, Julian Lettner, Prabhu Rajasekaran +4
cs.CRcs.PLarXiv:1806.04355v12018
Tranco: A Research-Oriented Top Sites Ranking Hardened Against Manipulation
Victor Le Pochat, Tom Van Goethem, Samaneh Tajalizadehkhoob +2
cs.CRcs.NIarXiv:1806.01156v32018
Certified Robustness to Adversarial Examples with Differential Privacy
Mathias Lecuyer, Vaggelis Atlidakis, Roxana Geambasu +2
stat.MLcs.AIcs.CRarXiv:1802.03471v42018
Adversarial Examples: Attacks and Defenses for Deep Learning
Xiaoyong Yuan, Pan He, Qile Zhu +1
cs.LGcs.CRcs.CVarXiv:1712.07107v32017
Automated Behavioral Analysis of Malware A Case Study of WannaCry Ransomware
Qian Chen, Robert A. Bridges
cs.CRarXiv:1709.08753v12017
Malware Guard Extension: Using SGX to Conceal Cache Attacks
Michael Schwarz, Samuel Weiser, Daniel Gruss +2
cs.CRarXiv:1702.08719v32017
Renyi Differential Privacy
Ilya Mironov
cs.CRarXiv:1702.07476v32017
HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation
Alessandro Zirilli, Davide Marincione, Evgenios M. Kornaropoulos +2
cs.CRcs.AIarXiv:2609.01730v12026
CRSF: Collusion-Resilient Privacy-Preserving Sensor Fusion with Byzantine-Robust Participation
Chao Yin, Haihong Tian, Zheng Yang +3
cs.CRarXiv:2609.01096v12026
Membership Inference Attacks against Machine Learning Models
Reza Shokri, Marco Stronati, Congzheng Song +1
cs.CRcs.LGstat.MLarXiv:1610.05820v22016
AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs
Chua Jin Chou, Sarang Nambiar, Murali Srinivasan +1
cs.CRarXiv:2609.01023v22026
Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
Mark Bun, Thomas Steinke
cs.CRcs.DScs.ITarXiv:1605.02065v12016
Centrally Banked Cryptocurrencies
George Danezis, Sarah Meiklejohn
cs.CRarXiv:1505.06895v22015
RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation
Yueyang Quan, Anjun Gao, Yufei Xia +2
cs.CRcs.AIcs.IRarXiv:2608.23965v12026
RAD: Rule-Augmented Relational Anomaly Detection
Noah Dahle, Anne Tumlin, Ngoc Tran +2
cs.LGcs.CRcs.DBarXiv:2608.23468v12026
AdaptPrint: Response-Adaptive Fingerprinting of Black-Box LLM Services
Yilin Li, Yifei Zhang, Guozhu Meng
cs.CRarXiv:2608.22213v12026
GhostTac: Manipulating Tactile Sensors without Physical Contact
Kun Wang, Xuancun Lu, Ruochen Zhou +6
cs.CRcs.ROarXiv:2608.20817v12026
Benchmarking Automated Security Patch Backporting: How Far Are We?
Jincheng Yang, Yulong Fu, Chengwei Liu +5
cs.SEcs.AIcs.CRarXiv:2608.17671v12026
Decomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services
Bowen Sun, Zhengyue Zhao, Xiaogeng Liu +2
cs.CRcs.CLarXiv:2608.17445v12026
Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees
Youwei Zhong, Ben Merbaum, Timos Antonopoulos +4
cs.LGcs.CRcs.LOarXiv:2608.17070v12026
Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis
Reza Fayyazi, Michael Zuzak, Shanchieh Jay Yang
cs.CRcs.AIarXiv:2608.16775v12026
Maintaining IoT Device Identification under Concept Drift via Budget-Aware Traffic Labeling
Shayan Azizi, Norihiro Okui, Masataka Nakahara +3
cs.NIcs.CRcs.LGarXiv:2608.15465v12026
From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding
Haoxuan Luo, Jameson Sandler, Ferdinando Fioretto
cs.CRcs.CLarXiv:2608.14787v12026
Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents
Yingqi Zhang
cs.OScs.AIcs.CRarXiv:2606.03895v22026
ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree
Vincent Koc, Patrick Erichsen, Jacob Tomlinson +3
cs.CRcs.AIcs.SEarXiv:2606.01494v12026

Cryptography and Security

Privacy Amplification Without Independence: How Far Negative Dependence Carries the Guarantees of Poisson Subsampling

Adversarial camera stickers: A physical camera-based attack on deep learning systems

IoTSense: Behavioral Fingerprinting of IoT Devices

Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

A Scenario-Based Evaluation of CRQC+AI Vulnerability Spectrum for TLS 1.3 Cryptographic Dependencies

Interpretable Deep Learning under Fire

NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing

Context Inference Attacks Without Jailbreaks

Explainable Adaptive Zero Trust Framework for AWS with Adversarial Robustness Evaluation

Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

If It Walks Like an Arbitrage: Protocol-Agnostic Detection with Decidable Structural Equivalence

Influence of Logging Frameworks on Bind9

ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling

Generative Adversarial Networks: A Survey Towards Private and Secure Applications

How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy

Detection of False Data Injection Attacks in Smart Grid: A Secure Federated Deep Learning Approach

IBM Federated Learning: an Enterprise Framework White Paper V0.1

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

threaTrace: Detecting and Tracing Host-based Threats in Node Level Through Provenance Graph Learning

Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion

SoK: Agentic Skills -- Beyond Tool Use in LLM Agents

nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data

Do you need a blockchain in construction? Use case categories and decision framework for DLT design options

Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

Machine Learning Based Network Vulnerability Analysis of Industrial Internet of Things

HEAX: An Architecture for Computing on Encrypted Data

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

Performance Comparison of Intrusion Detection Systems and Application of Machine Learning to Snort System

A new Backdoor Attack in CNNs by training set corruption without label poisoning

Decentralized Applications: The Blockchain-Empowered Software System

Federated Quantum Machine Learning

Exploring Connections Between Active Learning and Model Extraction

SoK: Sanitizing for Security

Tranco: A Research-Oriented Top Sites Ranking Hardened Against Manipulation

Certified Robustness to Adversarial Examples with Differential Privacy

Adversarial Examples: Attacks and Defenses for Deep Learning

Automated Behavioral Analysis of Malware A Case Study of WannaCry Ransomware

Malware Guard Extension: Using SGX to Conceal Cache Attacks

Renyi Differential Privacy

HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation

CRSF: Collusion-Resilient Privacy-Preserving Sensor Fusion with Byzantine-Robust Participation

Membership Inference Attacks against Machine Learning Models

AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs

Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds

Centrally Banked Cryptocurrencies

RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation

RAD: Rule-Augmented Relational Anomaly Detection

AdaptPrint: Response-Adaptive Fingerprinting of Black-Box LLM Services

GhostTac: Manipulating Tactile Sensors without Physical Contact

Benchmarking Automated Security Patch Backporting: How Far Are We?

Decomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services

Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees

Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis

Maintaining IoT Device Identification under Concept Drift via Budget-Aware Traffic Labeling

From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding

Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree