SecPapers

A living, searchable catalog of large language model security research.

Explore the web index | Browse all papers | Use the dataset | Methodology | Suggest a paper

SecPapers tracks both sides of LLM security: research that makes language models safer, and research that applies language models to cybersecurity. It queries arXiv every day, applies a transparent relevance filter, deduplicates paper revisions, and regenerates this repository from stable source data.

At a glance

2127 papers across 4 publication years. Latest arXiv metadata update: 2026-10-29.

Topic	Papers
Prompt Injection & Jailbreaks	486
Agent & Tool Security	520
Privacy & Data Leakage	330
Safety, Alignment & Misuse	502
Adversarial ML, Poisoning & Backdoors	466
Software & Vulnerability Security	632
Malware, Phishing & Cyber Defense	260
Evaluation, Benchmarks & Red Teaming	1002
Other LLM Security	140

Latest papers

Updated	Paper	Topics	Links
2026-10-29	The Privacy and Security Risks of Edge LLM Optimization Mingchen Li, Ren-Yi Huang, Dumindu Samaraweera, et al.	Privacy & Data Leakage	abstract / PDF
2026-10-29	Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training Qiusi Zhan, Nian Lyu, Stephanie Ding, et al.	Agent & Tool Security, Adversarial ML, Poisoning & Backdoors	abstract / PDF
2026-10-29	WAAA! Web Adversaries Against Web Agents Sohom Datta, Alex Nahapetyan, William Enck, et al.	Prompt Injection & Jailbreaks, Agent & Tool Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-29	Understanding and Mitigating Role Spoofing in LLMs Ezra Edelman, Benjamin Edelman, Surbhi Goel, et al.	Other LLM Security	abstract / PDF
2026-10-29	Robust Context-Aware Detection of Malicious Instructions in Text Buzhao Liu, Xinhang Ma, Yevgeniy Vorobeychik	Prompt Injection & Jailbreaks, Adversarial ML, Poisoning & Backdoors	abstract / PDF
2026-10-29	Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities Simin Chen, Yixin He, Suman Jana, et al.	Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-29	InferD: A Honeypot Framework for AI Inference Infrastructure Hicham Hammouchi, Gabriele Lenzini	Agent & Tool Security, Software & Vulnerability Security	abstract / PDF
2026-10-29	SEAL: Sealed Queries for Local Sanitization against Indirect Prompt Injection Doohyun Kim, Donghwa Kang, Mingyu Jun, et al.	Prompt Injection & Jailbreaks	abstract / PDF
2026-10-29	zkCraft: Prompt-Guided LLM as a Zero-Shot Mutation Pattern Oracle for TCCT-Powered ZK Fuzzing Rong Fu, Jia Yee Tan, Ziyu Kong, et al.	Privacy & Data Leakage, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-29	Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin Paula Chikaodinaka Anyanwu, Valdini Douglace Lemofouet, Blessing Ngozi Uzor, et al.	Safety, Alignment & Misuse, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-29	FuzzAgent: Multi-Agent System for End-to-End Evolutionary Library Fuzzing Yunlong Lyu, Peng Chen, Fengyi Wu, et al.	Agent & Tool Security, Safety, Alignment & Misuse	abstract / PDF
2026-10-29	Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy Hengyu Wu, Blaise Delattre, Yang Cao	Agent & Tool Security, Privacy & Data Leakage, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-29	Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems CheolWon Na, Hao Ni, Lukasz Szpruch, et al.	Agent & Tool Security, Adversarial ML, Poisoning & Backdoors, Software & Vulnerability Security	abstract / PDF
2026-10-29	The Illusion of Local Privacy: Confidentiality Boundary Failures in Consumer LLM Serving Systems Youssef Hamdi Zafan Ibrahim, Muhammad Ikram, Mohammed Khalaf Salama	Privacy & Data Leakage	abstract / PDF
2026-10-29	Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses Across Seven Large Language Models Md. Robiul Islam Niloy, Abu Sayed Md. Mostafizur Rahaman	Prompt Injection & Jailbreaks, Adversarial ML, Poisoning & Backdoors, Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF

Scope

Included work must mention an LLM or language-model concept and a concrete security, safety, privacy, abuse, or cyber-defense concept in its title or abstract. The taxonomy covers:

• Prompt injection and jailbreaks
• Agent and tool security
• Privacy, memorization, and data leakage
• Model safety, alignment, and misuse
• Adversarial attacks, poisoning, and backdoors
• Vulnerability discovery and secure software
• Malware, phishing, and threat intelligence
• Security evaluation, benchmarks, and red teaming

The catalog is automated discovery, not a quality ranking or endorsement. See the methodology for the query, scoring rules, known limitations, and correction process.

How it works

arXiv Atom API
      |
      v
query + pagination -> relevance scoring -> revision deduplication
      |                                          |
      +-------------------> data/papers.json <---+
                                  |
                                  v
            README.md + papers.md + CSV + web index

The collector uses only the Python standard library. There is no package installation step and no runtime dependency lockfile to maintain.

# Run tests
python3 -m unittest discover -s tests -v

# Fetch recent papers and regenerate every output
python3 scripts/collect.py

# Regenerate Markdown and CSV without network access
python3 scripts/collect.py --render-only

Search terms and taxonomy rules live in config/topics.json. The canonical record format is documented by data/schema.json. Updates run daily at 06:17 UTC and can also be started manually from the Actions tab.

Data use

• data/papers.json is the canonical, stable dataset.
• data/papers.csv is convenient for spreadsheets and analysis.
• papers.md is the human-readable catalog grouped by topic.
• docs/data contains compact, generated payloads for the SecPapers web index.
• Each record links to the authoritative arXiv abstract and PDF.
• Paper titles, abstracts, and author metadata remain attributable to their respective authors and are not relicensed by this repository's MIT license.

Contributing

False positives, missing papers, taxonomy improvements, and collector fixes are welcome. Read CONTRIBUTING.md before opening a pull request.

Acknowledgments

Paper metadata is provided by the arXiv API. SecPapers is not affiliated with or endorsed by arXiv. Please cite the original authors and papers when using this catalog in research.