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)

2,341 to 2,400 of 2,565

Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
Bryant Chen, Wilka Carvalho, Nathalie Baracaldo +5
cs.LGcs.CRstat.MLarXiv:1811.03728v12018
A Watermark for Large Language Models
John Kirchenbauer, Jonas Geiping, Yuxin Wen +3
cs.LGcs.CLcs.CRarXiv:2301.10226v42023
On Adaptive Attacks to Adversarial Example Defenses
Florian Tramer, Nicholas Carlini, Wieland Brendel +1
cs.LGcs.CRstat.MLarXiv:2002.08347v22020
Extracting Training Data from Diffusion Models
Nicholas Carlini, Jamie Hayes, Milad Nasr +6
cs.CRcs.CVcs.LGarXiv:2301.13188v12023
Spectral Signatures in Backdoor Attacks
Brandon Tran, Jerry Li, Aleksander Madry
cs.LGcs.CRstat.MLarXiv:1811.00636v12018
On Evaluating Adversarial Robustness
Nicholas Carlini, Anish Athalye, Nicolas Papernot +6
cs.LGcs.CRstat.MLarXiv:1902.06705v22019
Beyond Explicit Generators: Distribution-Free Linear-Decomposition Attacks on Public-Key Encryption
Ziyan Chen, Ding-Xuan Zhou
cs.CRarXiv:2608.20798v12026
Untangling Blockchain: A Data Processing View of Blockchain Systems
Tien Tuan Anh Dinh, Rui Liu, Meihui Zhang +3
cs.DBcs.CRarXiv:1708.05665v12017
Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection
Yisroel Mirsky, Tomer Doitshman, Yuval Elovici +1
cs.CRcs.AIcs.LGarXiv:1802.09089v22018
Robust Aggregation for Federated Learning
Krishna Pillutla, Sham M. Kakade, Zaid Harchaoui
stat.MLcs.CRcs.LGarXiv:1912.13445v22019
Temporal Risk on Satellites
Shiqi Liu, Kun Sun
cs.CRarXiv:2608.20575v12026
Masking Is Not Enough: Generative Restoration for Multimodal De-Identification in Medical AI
Shiva Shrestha, Zongxing Xie, Chen Zhao +3
cs.CVcs.CRarXiv:2608.21133v12026
Uncovering and Understanding Hidden Dependencies in the LLM API Reseller Ecosystem via Prefix-Cache Side Channels
Zimo Ji, Xin Wei, Congying Xu +5
cs.CRarXiv:2608.20732v12026
Workplace Surveillance and Insider Threat Risk Management: Legal Limits and Privacy Harms
Haywood Gelman, John D. Hastings, Suvineetha Herath +1
cs.CRarXiv:2608.21205v12026
Enabling Threshold Custody for the Lightning Network with Nested Threshold Multi-Signatures
Paul Gerhart, Nadav Kohen, Jesse Posner +1
cs.CRarXiv:2608.20705v12026
TraceGrant: A Contract-Governed Security Framework for the Task-Effect Lifecycle of Networked LLM Agents
Bohao Liao, Jingchao Wang, Qipeng Song +3
cs.CRarXiv:2608.21126v12026
Bootstrapping Mutual Attestation with Kleene's Second Recursion Theorem
Takuma Imamura
cs.CRmath.LOarXiv:2608.20671v12026
Generating Adversarial Examples with Adversarial Networks
Chaowei Xiao, Bo Li, Jun-Yan Zhu +3
cs.CRcs.CVstat.MLarXiv:1801.02610v52018
The Rising Cost of Trust: Practitioners' Trust Signals, Controls, and Responses in the Software Supply Chain
Ranindya Paramitha, Siri Paidipalli, Laurie Williams +1
cs.CRarXiv:2608.20675v12026
The Software Supply Chain as a Market for Lemons: A Multivocal Review of Trust Signal Collapse
Ranindya Paramitha, Christian Kästner, Laurie Williams
cs.CRcs.SEarXiv:2608.20678v12026
Eavesdropper-Blind Remote State Preparation and Applications to Quantum Public-Key Encryption
Kaniuar Bacho, Alexandru Cojocaru
quant-phcs.CRarXiv:2608.21241v12026
The Hidden Vulnerability of Distributed Learning in Byzantium
El Mahdi El Mhamdi, Rachid Guerraoui, Sébastien Rouault
stat.MLcs.CRcs.DCarXiv:1802.07927v22018
Privacy-Preserving Object Detection for Vision Transformer-Based Models
Homare Sueyoshi, Kiyoshi Nishikawa, Hitoshi Kiya
cs.CRcs.CVarXiv:2608.20712v12026
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
Songyang Liu, Chaozhuo Li, Chenxu Wang +8
cs.CRcs.AIarXiv:2603.24414v12026
Chat First, Worry Later: Understanding Individuals' Privacy Perceptions Using ChatGPT in a Work Context
Christoph Nirschl, Magdalena Glas, Gerhard Messmann +1
cs.HCcs.CRcs.CYarXiv:2608.20789v12026
A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security
Mohammed Ali Al-Garadi, Amr Mohamed, Abdulla Al-Ali +2
cs.CRcs.LGcs.NIarXiv:1807.11023v12018
STRIP: A Defence Against Trojan Attacks on Deep Neural Networks
Yansong Gao, Chang Xu, Derui Wang +3
cs.CRarXiv:1902.06531v22019
The Secrecy Capacity of the MIMO Wiretap Channel
Frédérique Oggier, Babak Hassibi
cs.ITcs.CRarXiv:0710.1920v12007
Deep Packet: A Novel Approach For Encrypted Traffic Classification Using Deep Learning
Mohammad Lotfollahi, Ramin Shirali Hossein Zade, Mahdi Jafari Siavoshani +1
cs.LGcs.CRcs.NIarXiv:1709.02656v32017
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Yi Liu, Weizhe Wang, Ruitao Feng +5
cs.CRcs.AIcs.CLarXiv:2601.10338v12026
Do Phone-Use Agents Respect Your Privacy?
Zhengyang Tang, Ke Ji, Xidong Wang +19
cs.CRcs.AIcs.CLarXiv:2604.00986v22026
AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration
Ruhao Liu, Weiqi Huang, Qi Li +1
cs.CRcs.CVarXiv:2604.01014v12026
AgentWatcher: A Rule-based Prompt Injection Monitor
Yanting Wang, Wei Zou, Runpeng Geng +1
cs.CRarXiv:2604.01194v22026
HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems
Asiri Dalugoda
cs.CRcs.MAarXiv:2604.04522v12026
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
Zijun Wang, Haoqin Tu, Letian Zhang +11
cs.CRcs.AIcs.CLarXiv:2604.04759v12026
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
Xuwei Ding, Skylar Zhai, Linxin Song +6
cs.CRcs.AIarXiv:2604.10577v22026
Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
Zhixin Lin, Jungang Li, Dongliang Xu +5
cs.AIcs.CRarXiv:2604.11259v12026
Mobile GUI Agents under Real-world Threats: Are We There Yet?
Guohong Liu, Jialei Ye, Jiacheng Liu +5
cs.CRcs.AIarXiv:2507.04227v22025
Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents
Yining Hong, Yining She, Eunsuk Kang +2
cs.SEcs.AIcs.CRarXiv:2604.15579v22026
EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection
Noor Islam S. Mohammad
cs.CRarXiv:2604.14663v12026
Modeling Sparse and Bursty Vulnerability Sightings: Forecasting Under Data Constraints
Cedric Bonhomme, Alexandre Dulaunoy
cs.CRarXiv:2604.16038v12026
Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
Jaechul Roh, Amir Houmansadr
cs.CRcs.SDarXiv:2604.16659v12026
Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories
Ivan Bercovich, Ivgeni Segal, Kexun Zhang +3
cs.CRcs.AIarXiv:2604.17596v12026
Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning
Xinyun Liu, Zhi Lu, Yu Chen +1
cs.CRcs.LGarXiv:2608.20580v12026
aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy
Fatih Deniz, Yazan Boshmaf, Dorde Popovic +1
cs.CRcs.LGarXiv:2608.20554v12026
BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning
Mouhamed Amine Bouchiha, Gregory Blanc, Yufei Han
cs.LGcs.CRcs.DCarXiv:2608.21137v12026
Faults That Fortify: CNN Adversarial Robustness via GPU Undervolting
Behnam Omidi, Ahmad Tahmasivand, Husam Alsyouri +4
cs.LGcs.ARcs.CRarXiv:2608.20572v12026
SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields
Baixin Li, Haiyun He
cs.CLcs.CRcs.LGarXiv:2608.20839v12026
Utility Under Attack: Agent Memory Poisoning and the Limits of Content Screening and Provenance Ranking
Arulnidhi Karunanidhi
cs.CRcs.AIarXiv:2608.21230v12026
AID-Guard: Stateful Authorization for Delegated Agent Effects
Yingzhe Tong, Leyu Dai, Songhui Guo
cs.CRcs.AIarXiv:2608.21159v12026
Vibe Coding and Web Application Security: A Twin-Prompt Study
Darko Andročec
cs.CRcs.AIarXiv:2608.20963v12026
ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents
Kai Wang, Zeming Wei, BiaoJie Zeng +7
cs.CRcs.AIarXiv:2608.21101v12026
Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
Balkrishna Giri, Md Toufique Hasan, Jussi Rasku +2
cs.SEcs.AIcs.CLarXiv:2608.21095v12026
$Z^2$-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
ARQ: Agentic CodeQL Query Refinement for C/C++ Vulnerability Detection
Chunyi Wang, Yunfei Ke, Junfeng Yang +2
cs.CRcs.AIarXiv:2608.20637v12026
AEGIS: Preventing Cross-Domain Resource Abuse in MCP
Shriti Priya, Teryl Taylor, Frederico Araujo
cs.CRcs.AIarXiv:2608.20481v12026
Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents
Wei Shao, Chongzhou Fang, Zuxiong Tan +4
cs.CRcs.AIarXiv:2608.20563v12026
Gazelle: A Low Latency Framework for Secure Neural Network Inference
Chiraag Juvekar, Vinod Vaikuntanathan, Anantha Chandrakasan
cs.CRarXiv:1801.05507v12018
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks
Yinpeng Dong, Tianyu Pang, Hang Su +1
cs.CVcs.CRcs.LGarXiv:1904.02884v12019
Towards Understanding the Robustness of Sparse Autoencoders
Ahson Saiyed, Sabrina Sadiekh, Chirag Agarwal
cs.LGcs.AIcs.CLarXiv:2604.18756v12026

Cryptography and Security

Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

A Watermark for Large Language Models

On Adaptive Attacks to Adversarial Example Defenses

Extracting Training Data from Diffusion Models

Spectral Signatures in Backdoor Attacks

On Evaluating Adversarial Robustness

Beyond Explicit Generators: Distribution-Free Linear-Decomposition Attacks on Public-Key Encryption

Untangling Blockchain: A Data Processing View of Blockchain Systems

Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection

Robust Aggregation for Federated Learning

Temporal Risk on Satellites

Masking Is Not Enough: Generative Restoration for Multimodal De-Identification in Medical AI

Uncovering and Understanding Hidden Dependencies in the LLM API Reseller Ecosystem via Prefix-Cache Side Channels

Workplace Surveillance and Insider Threat Risk Management: Legal Limits and Privacy Harms

Enabling Threshold Custody for the Lightning Network with Nested Threshold Multi-Signatures

TraceGrant: A Contract-Governed Security Framework for the Task-Effect Lifecycle of Networked LLM Agents

Bootstrapping Mutual Attestation with Kleene's Second Recursion Theorem

Generating Adversarial Examples with Adversarial Networks

The Rising Cost of Trust: Practitioners' Trust Signals, Controls, and Responses in the Software Supply Chain

The Software Supply Chain as a Market for Lemons: A Multivocal Review of Trust Signal Collapse

Eavesdropper-Blind Remote State Preparation and Applications to Quantum Public-Key Encryption

The Hidden Vulnerability of Distributed Learning in Byzantium

Privacy-Preserving Object Detection for Vision Transformer-Based Models

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

Chat First, Worry Later: Understanding Individuals' Privacy Perceptions Using ChatGPT in a Work Context

A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security

STRIP: A Defence Against Trojan Attacks on Deep Neural Networks

The Secrecy Capacity of the MIMO Wiretap Channel

Deep Packet: A Novel Approach For Encrypted Traffic Classification Using Deep Learning

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

Do Phone-Use Agents Respect Your Privacy?

AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration

AgentWatcher: A Rule-based Prompt Injection Monitor

HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization

Mobile GUI Agents under Real-world Threats: Are We There Yet?

Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents

EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection

Modeling Sparse and Bursty Vulnerability Sightings: Forecasting Under Data Constraints

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning

aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy

BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning

Faults That Fortify: CNN Adversarial Robustness via GPU Undervolting

SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields

Utility Under Attack: Agent Memory Poisoning and the Limits of Content Screening and Provenance Ranking

AID-Guard: Stateful Authorization for Delegated Agent Effects

Vibe Coding and Web Application Security: A Twin-Prompt Study

ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents

Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems

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

ARQ: Agentic CodeQL Query Refinement for C/C++ Vulnerability Detection

AEGIS: Preventing Cross-Domain Resource Abuse in MCP

Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents

Gazelle: A Low Latency Framework for Secure Neural Network Inference

Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks

Towards Understanding the Robustness of Sparse Autoencoders