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)

2,401 to 2,460 of 2,547

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
Kang Liu, Brendan Dolan-Gavitt, Siddharth Garg
cs.CRcs.LGarXiv:1805.12185v12018
Computer Science Conferences Should Require Nonrepudiable Experimental Results
Mamadou K. Keita, Christopher Homan
cs.CRarXiv:2605.08586v12026
Black-box Adversarial Attacks with Limited Queries and Information
Andrew Ilyas, Logan Engstrom, Anish Athalye +1
cs.CVcs.CRstat.MLarXiv:1804.08598v32018
N-BaIoT: Network-based Detection of IoT Botnet Attacks Using Deep Autoencoders
Yair Meidan, Michael Bohadana, Yael Mathov +4
cs.CRcs.LGarXiv:1805.03409v12018
A Survey on Homomorphic Encryption Schemes: Theory and Implementation
Abbas Acar, Hidayet Aksu, A. Selcuk Uluagac +1
cs.CRarXiv:1704.03578v22017
LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
Beomjin Ahn, Jungmin Kwon, Chanyong Jung +1
cs.CRcs.CVcs.LGarXiv:2605.13163v12026
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
Nicholas Carlini, Chang Liu, Úlfar Erlingsson +2
cs.LGcs.AIcs.CRarXiv:1802.08232v32018
Adversarial Training for Free!
Ali Shafahi, Mahyar Najibi, Amin Ghiasi +6
cs.LGcs.CRcs.CVarXiv:1904.12843v22019
Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
William Lugoloobi, Samuelle Marro, Jabez Magomere +2
cs.CRcs.AIcs.HCarXiv:2605.14786v12026
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
Qinbin Li, Zeyi Wen, Zhaomin Wu +5
cs.LGcs.CRcs.DBarXiv:1907.09693v72019
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
John T. Halloran, Noopur S. Bhatt
cs.CRcs.AIcs.LGarXiv:2605.19147v12026
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
Sangwoo Park, Woongyeong Yeo, Seanie Lee +6
cs.LGcs.AIcs.CRarXiv:2605.20258v12026
DeepXplore: Automated Whitebox Testing of Deep Learning Systems
Kexin Pei, Yinzhi Cao, Junfeng Yang +1
cs.LGcs.CRcs.SEarXiv:1705.06640v42017
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
Wieland Brendel, Jonas Rauber, Matthias Bethge
stat.MLcs.CRcs.CVarXiv:1712.04248v22017
Differentially Private Empirical Risk Minimization
Kamalika Chaudhuri, Claire Monteleoni, Anand D. Sarwate
cs.LGcs.AIcs.CRarXiv:0912.0071v52009
Graph-based Anomaly Detection and Description: A Survey
Leman Akoglu, Hanghang Tong, Danai Koutra
cs.SIcs.CRarXiv:1404.4679v22014
What Can We Learn Privately?
Shiva Prasad Kasiviswanathan, Homin K. Lee, Kobbi Nissim +2
cs.LGcs.CCcs.CRarXiv:0803.0924v32008
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
Minghong Fang, Xiaoyu Cao, Jinyuan Jia +1
cs.CRcs.DCcs.LGarXiv:1911.11815v42019
GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning
Haodong Zhao, Tianyi Xu, Tianhang Zhao +2
cs.CRarXiv:2605.26574v12026
Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
Battista Biggio, Fabio Roli
cs.CVcs.CRcs.GTarXiv:1712.03141v22017
Towards the Development of Realistic Botnet Dataset in the Internet of Things for Network Forensic Analytics: Bot-IoT Dataset
Nickolaos Koroniotis, Nour Moustafa, Elena Sitnikova +1
cs.CRarXiv:1811.00701v12018
Differentially Private Federated Learning: A Client Level Perspective
Robin C. Geyer, Tassilo Klein, Moin Nabi
cs.CRcs.LGstat.MLarXiv:1712.07557v22017
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
Weilin Xu, David Evans, Yanjun Qi
cs.CVcs.CRcs.LGarXiv:1704.01155v22017
Inverting Gradients -- How easy is it to break privacy in federated learning?
Jonas Geiping, Hartmut Bauermeister, Hannah Dröge +1
cs.CVcs.CRcs.LGarXiv:2003.14053v22020
How To Backdoor Federated Learning
Eugene Bagdasaryan, Andreas Veit, Yiqing Hua +2
cs.CRcs.LGarXiv:1807.00459v32018
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
Kai Greshake, Sahar Abdelnabi, Shailesh Mishra +3
cs.CRcs.AIcs.CLarXiv:2302.12173v22023
Exploiting Unintended Feature Leakage in Collaborative Learning
Luca Melis, Congzheng Song, Emiliano De Cristofaro +1
cs.CRcs.AIarXiv:1805.04049v32018
Poisoning Attacks against Support Vector Machines
Battista Biggio, Blaine Nelson, Pavel Laskov
cs.LGcs.CRstat.MLarXiv:1206.6389v32012
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
Nicolas Papernot, Patrick McDaniel, Ian Goodfellow
cs.CRcs.LGarXiv:1605.07277v12016
HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
Yajing Bai, Jinhao Duan, Jie Peng +4
cs.CRcs.AIarXiv:2608.17597v12026
Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
Nicholas Carlini, David Wagner
cs.LGcs.CRcs.CVarXiv:1705.07263v22017
Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense
Shuhao Zhang, Jiarui Li, Qi Cao +2
cs.CRcs.LGarXiv:2605.30837v22026
LLM Anonymization Against Agentic Re-Identification
Ziwen Li, Jianing Wen, Tianshi Li
cs.CRcs.CLarXiv:2605.30848v22026
Jailbroken: How Does LLM Safety Training Fail?
Alexander Wei, Nika Haghtalab, Jacob Steinhardt
cs.LGcs.CRarXiv:2307.02483v12023
Summaries:한국어
Large Language Models Hack Rewards, and Society
Wei Liu, Xinyi Mou, Hanqi Yan +2
cs.LGcs.AIcs.CLarXiv:2606.04075v22026
Adversarial Examples Are Not Bugs, They Are Features
Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras +3
stat.MLcs.CRcs.CVarXiv:1905.02175v42019
ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
Pin-Yu Chen, Huan Zhang, Yash Sharma +2
stat.MLcs.CRcs.LGarXiv:1708.03999v22017
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Xinyun Chen, Chang Liu, Bo Li +2
cs.CRcs.LGarXiv:1712.05526v12017
Evasion Attacks against Machine Learning at Test Time
Battista Biggio, Igino Corona, Davide Maiorca +5
cs.CRcs.LGarXiv:1708.06131v12017
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
Tianyu Gu, Brendan Dolan-Gavitt, Siddharth Garg
cs.CRcs.LGarXiv:1708.06733v22017
RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
Úlfar Erlingsson, Vasyl Pihur, Aleksandra Korolova
cs.CRarXiv:1407.6981v22014
Spectre Attacks: Exploiting Speculative Execution
Paul Kocher, Daniel Genkin, Daniel Gruss +7
cs.CRarXiv:1801.01203v12018
Deep Learning with Differential Privacy
Martín Abadi, Andy Chu, Ian Goodfellow +4
stat.MLcs.CRcs.LGarXiv:1607.00133v22016
CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills
Mingxiao Liu, Zhoumian Jiang, Jianan Ma +4
cs.CRcs.AIarXiv:2608.16246v12026
Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability
Yudong Gao, Linghan Chen, Wenhan Wu +5
cs.CRcs.AIarXiv:2608.15475v12026
STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation
Nawrin Tabassum, Yanzhao Wu
cs.CRcs.LGarXiv:2608.14861v12026
SkillHarness: Harnessing Safe Skills for Computer-Use Agents
Yurun Chen, Biao Yi, Keting Yin +1
cs.AIcs.CLcs.CRarXiv:2606.20636v12026
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Yitong Zhang, Shiteng Lu, Jia Li
cs.CRcs.AIcs.CLarXiv:2606.11817v12026
Ensemble Adversarial Training: Attacks and Defenses
Florian Tramèr, Alexey Kurakin, Nicolas Papernot +3
stat.MLcs.CRcs.LGarXiv:1705.07204v52017
Deep Leakage from Gradients
Ligeng Zhu, Zhijian Liu, Song Han
cs.LGcs.CRstat.MLarXiv:1906.08935v22019
Extracting Training Data from Large Language Models
Nicholas Carlini, Florian Tramer, Eric Wallace +9
cs.CRcs.CLcs.LGarXiv:2012.07805v22020
Federated Machine Learning: Concept and Applications
Qiang Yang, Yang Liu, Tianjian Chen +1
cs.AIcs.CRcs.LGarXiv:1902.04885v12019
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
Nicolas Papernot, Patrick McDaniel, Xi Wu +2
cs.CRcs.LGcs.NEarXiv:1511.04508v22015
Adversarial Machine Learning at Scale
Alexey Kurakin, Ian Goodfellow, Samy Bengio
cs.CVcs.CRcs.LGarXiv:1611.01236v22016
Universal and Transferable Adversarial Attacks on Aligned Language Models
Andy Zou, Zifan Wang, Nicholas Carlini +3
cs.CLcs.AIcs.CRarXiv:2307.15043v22023
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
Anish Athalye, Nicholas Carlini, David Wagner
cs.LGcs.AIcs.CRarXiv:1802.00420v42018
Practical Black-Box Attacks against Machine Learning
Nicolas Papernot, Patrick McDaniel, Ian Goodfellow +3
cs.CRcs.LGarXiv:1602.02697v42016
From Threat Intelligence to Detection: Knowledge-driven Enrichment and Template-based Rule Grounding for Automated Sigma Rule Generation
Sepehr Ghaffarzadegan, Boubakr Nour, Makan Pourzandi +2
cs.CRcs.AIarXiv:2608.19011v12026
Hyperledger Fabric: A Distributed Operating System for Permissioned Blockchains
Elli Androulaki, Artem Barger, Vita Bortnikov +18
cs.DCcs.CRarXiv:1801.10228v22018
Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents
Alexander Tu, Michael Tu
cs.CRcs.AIcs.LGarXiv:2608.18351v12026

Cryptography and Security

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks

Computer Science Conferences Should Require Nonrepudiable Experimental Results

Black-box Adversarial Attacks with Limited Queries and Information

N-BaIoT: Network-based Detection of IoT Botnet Attacks Using Deep Autoencoders

A Survey on Homomorphic Encryption Schemes: Theory and Implementation

LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters

The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks

Adversarial Training for Free!

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection

Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

DeepXplore: Automated Whitebox Testing of Deep Learning Systems

Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

Differentially Private Empirical Risk Minimization

Graph-based Anomaly Detection and Description: A Survey

What Can We Learn Privately?

Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning

Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning

Towards the Development of Realistic Botnet Dataset in the Internet of Things for Network Forensic Analytics: Bot-IoT Dataset

Differentially Private Federated Learning: A Client Level Perspective

Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks

Inverting Gradients -- How easy is it to break privacy in federated learning?

How To Backdoor Federated Learning

Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Exploiting Unintended Feature Leakage in Collaborative Learning

Poisoning Attacks against Support Vector Machines

Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples

HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety

Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods

Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense

LLM Anonymization Against Agentic Re-Identification

Jailbroken: How Does LLM Safety Training Fail?

Large Language Models Hack Rewards, and Society

Adversarial Examples Are Not Bugs, They Are Features

ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models

Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Evasion Attacks against Machine Learning at Test Time

BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response

Spectre Attacks: Exploiting Speculative Execution

Deep Learning with Differential Privacy

CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills

Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability

STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation

SkillHarness: Harnessing Safe Skills for Computer-Use Agents

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

Ensemble Adversarial Training: Attacks and Defenses

Deep Leakage from Gradients

Extracting Training Data from Large Language Models

Federated Machine Learning: Concept and Applications

Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks

Adversarial Machine Learning at Scale

Universal and Transferable Adversarial Attacks on Aligned Language Models

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

Practical Black-Box Attacks against Machine Learning

From Threat Intelligence to Detection: Knowledge-driven Enrichment and Template-based Rule Grounding for Automated Sigma Rule Generation

Hyperledger Fabric: A Distributed Operating System for Permissioned Blockchains

Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents