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)

2,461 to 2,520 of 2,547

Are LLMs Safe Beyond Text: Do Emojis Expose Gaps in Safety Evaluation
M P V S Gopinadh
cs.CLcs.AIcs.CRarXiv:2608.18164v12026
Abliteration Mitigation via Refusal Aliases
Nathan Truong
cs.CLcs.AIcs.CRarXiv:2608.18093v12026
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication
Ramneet Kaur, Pradyumna Chari, Ramesh Raskar +3
cs.AIcs.CRarXiv:2608.19161v12026
CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence
Yutong Cheng, Changze Li, Qian Cui +4
cs.AIcs.CRarXiv:2608.18613v12026
Evaluating Structured Information Extraction with Open Models in a High Risk Public Sector Application
Elias Schubert, Felix Bießmann
cs.AIcs.CRcs.IRarXiv:2608.18289v12026
Advances and Open Problems in Federated Learning
Peter Kairouz, H. Brendan McMahan, Brendan Avent +56
cs.LGcs.CRstat.MLarXiv:1912.04977v32019
MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering Model
Ali Habibzadeh, Farid Feyzi, Reza Ebrahimi Atani
cs.IRcs.CRcs.LGarXiv:2608.16921v22026
Digital Twin-Based Intrusion Detection for Vehicle Powertrain CAN Bus Systems
Araf Rahman, M Sabbir Salek, Mashrur Chowdhury
cs.CRcs.LGarXiv:2608.17093v12026
Picture the Epsilon: Pursuing Identity-Level Privacy Guarantees for Images
Arman Zareian Jahromi, Vishnu Bondalakunta, Mohammad Akbar Bin Shah +3
cs.CRcs.LGarXiv:2608.17147v12026
Provenance, Not Behaviour: A Serialisation Artifact in Edge-IIoTset and a Leakage-Free Benchmark for Precision-Agriculture Intrusion Detection
Mostafa M. Galal
cs.CRcs.LGarXiv:2608.15761v12026
Benchmarking Quantum Machine Learning for Power-System Attack Detection: Evaluation Choices Decide the Outcome Before the Models Do
Md Rezwanul Islam
cs.LGcs.CRstat.MLarXiv:2608.15617v12026
Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution
Adam Mazzocchetti
cs.AIcs.CEcs.CRarXiv:2608.16891v12026
The Ghosts of Polymarket: When Off-Chain Matches Meet On-Chain Reverts
Yiming Shen, Yuhan Jin, Shuohan Wu +2
cs.CRarXiv:2606.16852v12026
Authorization Before Context: A Model-Neutral Audience Boundary Against Cross-Audience Memory Leakage in Agentic Systems
Sibo Liu
cs.CRcs.AIarXiv:2608.17148v12026
Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline
Mikhail Surikov
cs.CRcs.AIcs.SEarXiv:2608.16187v12026
The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence
Neeraj Kumar Singh Beshane
cs.CRcs.AIarXiv:2608.17176v12026
AudioTQ: A Data-Oblivious 6-Bit CPU Audio Codec via Randomized Hadamard Rotation and Lloyd-Max Quantization
Sahil Gangurde
cs.SDcs.AIcs.CRarXiv:2608.15369v12026
When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse
Yingtao Ren, Ziyi Zhao, Yiwei Fu +3
cs.CRarXiv:2608.06947v12026
Chameleon: An Adaptive AI-Driven Honeypot Architecture Using Threat-Calibrated Particle Swarm Optimization and Semantic Deception Rapidly-Exploring Random Trees
Rohit Swami, Tushar Singh, Akash Warde +1
cs.CRcs.AIcs.NEarXiv:2608.15407v12026
WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing
Zhiyu Zhang, Tingyue Wen, Senke Sun +2
cs.CRcs.AIcs.SEarXiv:2608.15092v12026
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
Charbel El Feghali, Arkil Patel, Nicholas Meade +3
cs.CRcs.CLarXiv:2606.21638v12026
Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models
Mark Russinovich
cs.AIcs.CRarXiv:2608.17202v12026
The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges
Maosen Zhang, Jianshuo Dong, Boting Lu +5
cs.CRcs.AIarXiv:2608.17829v12026
MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps
Sujin Chen, Lijun Li, Tianyi Du +1
cs.CRcs.AIarXiv:2608.17659v12026
BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data
Ishpuneet Singh, Gursmeep Kaur, Uday Pratap Singh Atwal +3
cs.CRcs.AIcs.CVarXiv:2605.10867v22026
LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra +6
cs.LGcs.CLcs.CRarXiv:2605.14454v12026
Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models
Malikeh Ehghaghi, Boglárka Ecsedi, Marsha Chechik +1
cs.LGcs.AIcs.CRarXiv:2606.11409v12026
SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system
Yuhan Meng, Shaofei Li, Jionghao Huang +8
cs.CRcs.AIcs.MAarXiv:2608.15012v12026
Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference
Yiran Gao, Juntao Chen, Tao Li
cs.CRcs.AIarXiv:2608.15016v12026
IP Protection in the Era of Visual Generative AI: A Survey
Zhuan Shi, Shunchang Liu, Alireza Dehghanpour Farashah +8
cs.CVcs.CRcs.LGarXiv:2608.14730v12026
Workspace Topology as an Attack Vector in Agentic Coding Assistants
Alexandre G. R. Day, Pradeep Yadlapalli, Sriram Venkatapathy +9
cs.CRcs.AIcs.CLarXiv:2608.14876v12026
Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets
Zhida He, Xiaoyu Wen, Han Qi +5
cs.CRcs.AIarXiv:2608.17360v12026
TwinGridShield: Consequence-Aware Runtime Authorization for LLM Grid-Agent Actions
Md Fazley Rafy
cs.AIcs.CRarXiv:2608.15391v12026
Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations
Alizishaan Khatri
cs.CRcs.AIcs.LGarXiv:2608.16970v12026
Structured Driving-State Narratives for Small Language Model-Based GNSS Spoofing Detection
Abyad Enan, Sagar Dasgupta, Mizanur Rahman +1
cs.CRcs.AIarXiv:2608.17092v12026
Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models
Nyamtulla Shaik, Fengjun Li, Bo Luo
cs.AIcs.CRarXiv:2608.17183v12026
PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance
Rabimba Karanjai, Yang Lu, Richard Williamson +5
cs.CRcs.AIarXiv:2608.17220v12026
When Agents Act on Web3: An Attack-Surface Survey of MCP, Skills, and Tool Calling
Rabimba Karanjai, Yang Lu, Nour Diallo +4
cs.CRcs.AIarXiv:2608.17275v12026
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
Ziqian Zhong, Ivgeni Segal, Ivan Bercovich +3
cs.CRcs.AIcs.LGarXiv:2606.08960v12026
RedAct: Redacting Agent Capability Traces for Procedural Skill Protection
Shuwen Xu, Zhitao He, Yi R. Fung
cs.CRcs.CLarXiv:2606.10813v32026
FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting
Zhenyan Liu, Hua Zhang, Haoran Gao +6
cs.CRcs.LGarXiv:2608.15310v12026
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
Xinjie Shen, Rongzhe Wei, Peizhi Niu +6
cs.CLcs.AIcs.CRarXiv:2605.05630v22026
Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles
Anik Jha
cs.CRcs.LGarXiv:2608.16190v12026
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
BraveGuard: From Open-World Threats to Safer Computer-Use Agents
Yunhao Feng, Xiaohu Du, Xinhao Deng +13
cs.CRcs.CLarXiv:2606.01166v22026
DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption
Chang Liu, Yuni Lai, Mingyue Cui +5
cs.CRcs.CLarXiv:2608.16536v12026
SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
Qi Hu, Yifeng Tang, Qinghua Wang +7
cs.SEcs.CRarXiv:2606.01317v12026
SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
Yipeng Ouyang, Yi Xiao, Yuhao Gu +1
cs.CRcs.AIarXiv:2605.03353v42026
Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching
Ye Lu, Shen Wang, Zhaoyang Zhang +4
cs.CVcs.AIcs.CRarXiv:2608.16791v12026
GEO-Flag: Detecting and Measuring GEO-Optimized Web Content
Junjie Chu, Ye Leng, Mingjie Li +3
cs.LGcs.CRcs.IRarXiv:2608.16824v12026
Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection
Zonghao Ying, Xiangfan Wu, Huiyu Wu +4
cs.CRarXiv:2608.16393v22026
LLMs for Zero-Shot Threat Detection via Structured Risk Indicators
Abdullah Alghamdi, Siamak Layeghy, Marius Portmann
cs.CRcs.LGcs.NIarXiv:2608.16508v12026
Digital Twin Degradation: Detecting Cyber Physical Attacks via Temporal Inconsistencies
Konstantinos E. Kampourakis, Vasileios Gkioulos, Sokratis Katsikas
cs.CRcs.AIcs.LGarXiv:2608.16159v12026
Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm
Hidayet Aksu
cs.CRcs.AIarXiv:2608.16177v22026
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
cs.AIcs.CLcs.CRarXiv:2605.29801v12026
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
Zhenxin Ai, Haiyun He
cs.CRcs.AIarXiv:2605.10977v22026
Beyond Direct Access: Resource Hijacking in LLM Agents
Puyu Zeng, Qibing Ren
cs.CRcs.AIarXiv:2608.15108v12026
Poise: Position-Aware One-Instruction Skill Injection for Silent Execution on LLM Agents
Haochang Hao, Dehai Min, Zhifang Zhang +4
cs.CRcs.AIcs.CLarXiv:2606.07943v22026
Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation
Jasmine Brazilek, Maheep Chaudhary, Zoe Lu +1
cs.MAcs.AIcs.CRarXiv:2607.15434v52026
An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning
Wenjing Wei, Alla Jammine, Farid Nait-Abdesselam
cs.CRcs.LGarXiv:2608.15153v12026

Cryptography and Security

Are LLMs Safe Beyond Text: Do Emojis Expose Gaps in Safety Evaluation

Abliteration Mitigation via Refusal Aliases

Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication

CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence

Evaluating Structured Information Extraction with Open Models in a High Risk Public Sector Application

Advances and Open Problems in Federated Learning

MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering Model

Digital Twin-Based Intrusion Detection for Vehicle Powertrain CAN Bus Systems

Picture the Epsilon: Pursuing Identity-Level Privacy Guarantees for Images

Provenance, Not Behaviour: A Serialisation Artifact in Edge-IIoTset and a Leakage-Free Benchmark for Precision-Agriculture Intrusion Detection

Benchmarking Quantum Machine Learning for Power-System Attack Detection: Evaluation Choices Decide the Outcome Before the Models Do

Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution

The Ghosts of Polymarket: When Off-Chain Matches Meet On-Chain Reverts

Authorization Before Context: A Model-Neutral Audience Boundary Against Cross-Audience Memory Leakage in Agentic Systems

Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline

The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence

AudioTQ: A Data-Oblivious 6-Bit CPU Audio Codec via Randomized Hadamard Rotation and Lloyd-Max Quantization

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse

Chameleon: An Adaptive AI-Driven Honeypot Architecture Using Threat-Calibrated Particle Swarm Optimization and Semantic Deception Rapidly-Exploring Random Trees

WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing

Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs

Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models

The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges

MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps

BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference

IP Protection in the Era of Visual Generative AI: A Survey

Workspace Topology as an Attack Vector in Agentic Coding Assistants

Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets

TwinGridShield: Consequence-Aware Runtime Authorization for LLM Grid-Agent Actions

Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations

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

Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models

PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance

When Agents Act on Web3: An Attack-Surface Survey of MCP, Skills, and Tool Calling

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

RedAct: Redacting Agent Capability Traces for Procedural Skill Protection

FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue

Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles

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

BraveGuard: From Open-World Threats to Safer Computer-Use Agents

DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption

SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces

SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents

Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching

GEO-Flag: Detecting and Measuring GEO-Optimized Web Content

Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection

LLMs for Zero-Shot Threat Detection via Structured Risk Indicators

Digital Twin Degradation: Detecting Cyber Physical Attacks via Temporal Inconsistencies

Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

Beyond Direct Access: Resource Hijacking in LLM Agents

Poise: Position-Aware One-Instruction Skill Injection for Silent Execution on LLM Agents

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation

An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning