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)

961 to 1,020 of 2,549

Curriculum Adversarial Training
Qi-Zhi Cai, Min Du, Chang Liu +1
cs.LGcs.CRstat.MLarXiv:1805.04807v12018
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning
Linyang Li, Demin Song, Xiaonan Li +3
cs.CRcs.CLarXiv:2108.13888v12021
LlamaFirewall: An open source guardrail system for building secure AI agents
Sahana Chennabasappa, Cyrus Nikolaidis, Daniel Song +16
cs.CRcs.AIarXiv:2505.03574v12025
A combination chaotic system and application in color image encryption
R. Parvaz, M. Zarebnia
cs.ITcs.CRarXiv:1708.01862v12017
MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
Brandon Radosevich, John Halloran
cs.CRcs.AIcs.LGarXiv:2504.03767v22025
SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment
Qingyu Meng, Yiwei Zha, Jiahuan Pei +3
cs.LGcs.AIcs.CRarXiv:2609.02293v12026
The Privacy Policy Landscape After the GDPR
Thomas Linden, Rishabh Khandelwal, Hamza Harkous +1
cs.CRcs.CLcs.CYarXiv:1809.08396v32018
Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
Tiansheng Huang, Sihao Hu, Fatih Ilhan +4
cs.CRcs.AIcs.LGarXiv:2503.00555v22025
Reveree: Diagnosing LLM Reverse-Engineering Agents
Hadjer Benkraouda, Hongyu Cai, Berkay Celik +1
cs.CRarXiv:2609.01185v12026
GlitchLab: A Hardware-in-the-Loop Optimizer for Physical Fault Injection
Tanvir Hossain, Abhinav Mahadevan, Jasper Van Woudenberg +2
cs.CRarXiv:2609.00502v12026
Red-Teaming LLM Multi-Agent Systems via Communication Attacks
Pengfei He, Yupin Lin, Shen Dong +3
cs.CRarXiv:2502.14847v22025
DeepCorr: Strong Flow Correlation Attacks on Tor Using Deep Learning
Milad Nasr, Alireza Bahramali, Amir Houmansadr
cs.CRcs.LGarXiv:1808.07285v12018
Sponge Examples: Energy-Latency Attacks on Neural Networks
Ilia Shumailov, Yiren Zhao, Daniel Bates +3
cs.LGcs.CLcs.CRarXiv:2006.03463v22020
Algorand
Jing Chen, Silvio Micali
cs.CRcs.DCarXiv:1607.01341v92016
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
Rui Yang, Junjie Xu, Zhengyu Liu +4
cs.CRcs.AIarXiv:2609.00595v12026
Prompt Injection Attack to Tool Selection in LLM Agents
Jiawen Shi, Zenghui Yuan, Guiyao Tie +3
cs.CRarXiv:2504.19793v32025
Don't Trust the Code, Check Its Effects: Runtime Refinement for Regenerated Systems Code Under an Adversarial Generator
Jinhao Hu, Ashvin Goel, Laurent Bindschaedler
cs.CRarXiv:2609.00430v12026
Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry
Shengfang Zhai, Leo Marchyok, Yuling Shi +4
cs.CLcs.CRarXiv:2609.00873v12026
Securing AI Agents with Information-Flow Control
Manuel Costa, Boris Köpf, Aashish Kolluri +6
cs.CRcs.AIarXiv:2505.23643v22025
Quantum-Based Solutions for Security Enhancement in Open Radio Access Networks
Dzung Quoc Ngo, Tharmikka Raveendranathan, Tuan Anh Le +3
cs.CRcs.ETarXiv:2608.28480v12026
Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings
Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon +2
cs.CRcs.CLcs.LGarXiv:2608.17556v12026
Automated Vulnerability Injection in Smart Contracts Using Large Language Models
Luca Migliaccio, Roberto Natella, Naghmeh Ivaki +2
cs.SEcs.AIcs.CRarXiv:2609.02624v12026
Summaries:한국어
POLYFLOW: A Neuro-Symbolic Framework for Static Cross-Language Information Flow Analysis
Haoran Yang, Zhixuan Zhong, Jiawei Guo +1
cs.CRcs.PLcs.SEarXiv:2608.29808v12026
COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models
Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie +3
cs.CRcs.AIarXiv:2608.17234v12026
Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem Proving
Devakh Rashie, Veda Rashi
cs.LOcs.AIcs.CRarXiv:2604.01483v12026
Fast, Reliable, and Secure Drone Communication: A Comprehensive Survey
Vikas Hassija, Vinay Chamola, Adhar Agrawal +5
cs.CRarXiv:2105.01347v12021
Trident: Efficient 4PC Framework for Privacy Preserving Machine Learning
Harsh Chaudhari, Rahul Rachuri, Ajith Suresh
cs.LGcs.CRstat.MLarXiv:1912.02631v22019
DL-Droid: Deep learning based android malware detection using real devices
Mohammed K. Alzaylaee, Suleiman Y. Yerima, Sakir Sezer
cs.CRcs.LGcs.NEarXiv:1911.10113v12019
TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time
Feargus Pendlebury, Fabio Pierazzi, Roberto Jordaney +2
cs.CRcs.LGarXiv:1807.07838v42018
Backdoor Learning: A Survey
Yiming Li, Yong Jiang, Zhifeng Li +1
cs.CRcs.CVcs.LGarXiv:2007.08745v52020
Demographic Bias in Biometrics: A Survey on an Emerging Challenge
P. Drozdowski, C. Rathgeb, A. Dantcheva +2
cs.CYcs.CRcs.CVarXiv:2003.02488v22020
Adversarial Attack and Defense on Graph Data: A Survey
Lichao Sun, Yingtong Dou, Carl Yang +5
cs.CRcs.AIcs.SIarXiv:1812.10528v42018
Model-Reuse Attacks on Deep Learning Systems
Yujie Ji, Xinyang Zhang, Shouling Ji +2
cs.CRarXiv:1812.00483v12018
The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
Feng He, Tianqing Zhu, Dayong Ye +3
cs.CRarXiv:2407.19354v22024
Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings
Yubo Wang, Shujie Cui, James Bailey +5
cs.LGcs.AIcs.CRarXiv:2608.18610v12026
Bounded Agents: Delegation Security for Multi-Agent AI Systems
Xabier Muruaga
cs.AIcs.CRarXiv:2608.15888v12026
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
Travis Lelle
cs.CRcs.AIcs.CLarXiv:2605.30189v12026
The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus
Syed Muhammad Aqdas Rizvi
cs.AIcs.CLcs.CRarXiv:2604.16913v12026
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Briland Hitaj, Giuseppe Ateniese, Fernando Perez-Cruz
cs.CRcs.LGstat.MLarXiv:1702.07464v32017
On the Additive FFT Techniques over Binary Extension Fields
Susanta Samanta, Mohammadtaghi Badakhshan, Guang Gong
cs.CRarXiv:2608.20855v12026
The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
Milad Nasr, Nicholas Carlini, Chawin Sitawarin +11
cs.LGcs.CRarXiv:2510.09023v12025
PromptArmor: Simple yet Effective Prompt Injection Defenses
Tianneng Shi, Kaijie Zhu, Zhun Wang +13
cs.CRcs.AIarXiv:2507.15219v12025
ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
Zhaorun Chen, Mintong Kang, Bo Li
cs.LGcs.CRarXiv:2503.22738v22025
Light Commands: Laser-Based Audio Injection Attacks on Voice-Controllable Systems
Takeshi Sugawara, Benjamin Cyr, Sara Rampazzi +2
cs.CRarXiv:2006.11946v12020
Certified Defenses for Adversarial Patches
Ping-Yeh Chiang, Renkun Ni, Ahmed Abdelkader +3
cs.CRcs.LGstat.MLarXiv:2003.06693v22020
SecAlign: Defending Against Prompt Injection with Preference Optimization
Sizhe Chen, Arman Zharmagambetov, Saeed Mahloujifar +3
cs.CRcs.LGarXiv:2410.05451v32024
BlockHammer: Preventing RowHammer at Low Cost by Blacklisting Rapidly-Accessed DRAM Rows
Abdullah Giray Yağlıkçı, Minesh Patel, Jeremie S. Kim +9
cs.CRcs.ARarXiv:2102.05981v22021
DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks
Yupei Liu, Yuqi Jia, Jinyuan Jia +2
cs.CRcs.AIarXiv:2504.11358v42025
On the Importance of Difficulty Calibration in Membership Inference Attacks
Lauren Watson, Chuan Guo, Graham Cormode +1
cs.CRcs.LGarXiv:2111.08440v22021
Cryptanalysis of a Chaotic Image Encryption Algorithm Based on Information Entropy
Chengqing Li, Dongdong Lin, Bingbing Feng +2
cs.CRarXiv:1803.10024v22018
A SoK for SoCs: Reading the TI Leaves on AI for Cyber Threat Intelligence Generation and Sharing
Saastha Vasan, Hadjer Benkraouda, Jizhou Chen +8
cs.CRarXiv:2609.01174v12026
WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
Ivan Evtimov, Arman Zharmagambetov, Aaron Grattafiori +2
cs.CRcs.AIarXiv:2504.18575v32025
NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
Anjun Gao, Yueyang Quan, Yufei Xia +2
cs.CRcs.AIcs.IRarXiv:2608.23959v12026
MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning
Xukun Luan, Jinyan Liu, Yuhui Gong +4
cs.CRcs.LGarXiv:2608.17722v12026
On the Pseudo-Mixing of Kac's Walk
Natesh S. Pillai, Aaron Smith, Vinod Vaikuntanathan
math.PRcs.CRcs.LGarXiv:2608.17374v12026
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Salman Rahman, Liwei Jiang, James Shiffer +7
cs.CRcs.AIcs.CLarXiv:2504.13203v22025
AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning
Jinyuan Jia, Neil Zhenqiang Gong
cs.CRstat.MLarXiv:1805.04810v22018
When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning
Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2
cs.CRcs.AIarXiv:2609.01455v12026
SmartBugs: A Framework to Analyze Solidity Smart Contracts
João F. Ferreira, Pedro Cruz, Thomas Durieux +1
cs.SEcs.CRarXiv:2007.04771v22020
Automated Poisoning Attacks and Defenses in Malware Detection Systems: An Adversarial Machine Learning Approach
Sen Chen, Minhui Xue, Lingling Fan +4
cs.CRarXiv:1706.04146v32017

Cryptography and Security

Curriculum Adversarial Training

Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning

LlamaFirewall: An open source guardrail system for building secure AI agents

A combination chaotic system and application in color image encryption

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits

SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment

The Privacy Policy Landscape After the GDPR

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable

Reveree: Diagnosing LLM Reverse-Engineering Agents

GlitchLab: A Hardware-in-the-Loop Optimizer for Physical Fault Injection

Red-Teaming LLM Multi-Agent Systems via Communication Attacks

DeepCorr: Strong Flow Correlation Attacks on Tor Using Deep Learning

Sponge Examples: Energy-Latency Attacks on Neural Networks

Algorand

SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems

Prompt Injection Attack to Tool Selection in LLM Agents

Don't Trust the Code, Check Its Effects: Runtime Refinement for Regenerated Systems Code Under an Adversarial Generator

Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry

Securing AI Agents with Information-Flow Control

Quantum-Based Solutions for Security Enhancement in Open Radio Access Networks

Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings

Automated Vulnerability Injection in Smart Contracts Using Large Language Models

POLYFLOW: A Neuro-Symbolic Framework for Static Cross-Language Information Flow Analysis

COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models

Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem Proving

Fast, Reliable, and Secure Drone Communication: A Comprehensive Survey

Trident: Efficient 4PC Framework for Privacy Preserving Machine Learning

DL-Droid: Deep learning based android malware detection using real devices

TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time

Backdoor Learning: A Survey

Demographic Bias in Biometrics: A Survey on an Emerging Challenge

Adversarial Attack and Defense on Graph Data: A Survey

Model-Reuse Attacks on Deep Learning Systems

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

Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings

Bounded Agents: Delegation Security for Multi-Agent AI Systems

Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection

The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus

Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning

On the Additive FFT Techniques over Binary Extension Fields

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections

PromptArmor: Simple yet Effective Prompt Injection Defenses

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning

Light Commands: Laser-Based Audio Injection Attacks on Voice-Controllable Systems

Certified Defenses for Adversarial Patches

SecAlign: Defending Against Prompt Injection with Preference Optimization

BlockHammer: Preventing RowHammer at Low Cost by Blacklisting Rapidly-Accessed DRAM Rows

DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks

On the Importance of Difficulty Calibration in Membership Inference Attacks

Cryptanalysis of a Chaotic Image Encryption Algorithm Based on Information Entropy

A SoK for SoCs: Reading the TI Leaves on AI for Cyber Threat Intelligence Generation and Sharing

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks

NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution

MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning

On the Pseudo-Mixing of Kac's Walk

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning

When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

SmartBugs: A Framework to Analyze Solidity Smart Contracts

Automated Poisoning Attacks and Defenses in Malware Detection Systems: An Adversarial Machine Learning Approach