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

1189 papers across 4 publication years. Latest arXiv metadata update: 2026-09-10.

Topic	Papers
Prompt Injection & Jailbreaks	258
Agent & Tool Security	291
Privacy & Data Leakage	175
Safety, Alignment & Misuse	286
Adversarial ML, Poisoning & Backdoors	259
Software & Vulnerability Security	382
Malware, Phishing & Cyber Defense	149
Evaluation, Benchmarks & Red Teaming	560
Other LLM Security	87

Latest papers

Updated	Paper	Topics	Links
2026-09-10	BlueSTAR: Tiered Agentic Architecture for Autonomous Cyber Defense Simona Boboila, Xavier Cadet, Edward Koh, et al.	Agent & Tool Security	abstract / PDF
2026-09-10	SpecGuard: Inference-Time Backdoor Detection For Free Rui Wen, Ahmed Salem, Andrew Paverd, et al.	Adversarial ML, Poisoning & Backdoors	abstract / PDF
2026-09-10	Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs Jordi Luque, Fernando López, Aleix Sant	Privacy & Data Leakage	abstract / PDF
2026-09-10	VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use Juan S. Santillana	Agent & Tool Security, Malware, Phishing & Cyber Defense	abstract / PDF
2026-09-10	Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation Junyu Lu, Kaiyuan Liu, Kaichun Wang, et al.	Adversarial ML, Poisoning & Backdoors, Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-09-10	Exploring the Role of Security Experience and ChatGPT Usage Strategies on Secure Software Engineering Education Alessio Ferrari, Minh An Nguyen, Kushal Ramkumar, et al.	Software & Vulnerability Security, Malware, Phishing & Cyber Defense	abstract / PDF
2026-09-10	Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model Hyojung Han	Safety, Alignment & Misuse, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-09-10	Privacy Auditing with Zero (0) Training Run Tudor Cebere, Mathieu Even, Linus Bleistein, et al.	Privacy & Data Leakage, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-09-10	ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks Haozhe Lu, Jiaqi Li, Xinyuan Zhu, et al.	Adversarial ML, Poisoning & Backdoors	abstract / PDF
2026-09-10	DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation Attacks Rui Cao, Shaojing Fan, Liming Fang, et al.	Software & Vulnerability Security	abstract / PDF
2026-09-10	Demystifying the Privacy-Utility Trade-off in LLM Interactions Zhenhua Liu, Zhanxu Xie, Junjie Yu, et al.	Privacy & Data Leakage	abstract / PDF
2026-09-10	LLMVul: A Vulnerability-Labeled Dataset of LLM-Generated C/C++ Functions from Real Production Repositories Mohammad Farhad, Shuvalaxmi Dass	Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-09-09	DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents Asif Pinjari, Mithun Paul Saint-Germain	Prompt Injection & Jailbreaks, Agent & Tool Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-09-09	A2ABreak: Systematic Security Analysis of the A2A Protocol Alireza Lotfi, Mirza Masfiqur Rahman, Imtiaz Karim, et al.	Agent & Tool Security, Software & Vulnerability Security	abstract / PDF
2026-09-09	No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers Zehua Zhang, Jie Hu, Pratham Hegde, et al.	Prompt Injection & Jailbreaks, Agent & Tool Security, Software & Vulnerability Security	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.