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

2247 papers across 4 publication years. Latest arXiv metadata update: 2026-11-05.

Topic	Papers
Prompt Injection & Jailbreaks	522
Agent & Tool Security	554
Privacy & Data Leakage	351
Safety, Alignment & Misuse	523
Adversarial ML, Poisoning & Backdoors	490
Software & Vulnerability Security	663
Malware, Phishing & Cyber Defense	272
Evaluation, Benchmarks & Red Teaming	1052
Other LLM Security	147

Latest papers

Updated	Paper	Topics	Links
2026-11-05	The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI Julian Kunkel, Ali Doosthosseini	Prompt Injection & Jailbreaks, Agent & Tool Security, Privacy & Data Leakage	abstract / PDF
2026-11-05	LABBA: LLM-Assisted Behavioral Biometric Authentication Howard Halim, Eyasu Getahun Chekole, Jianying Zhou	Adversarial ML, Poisoning & Backdoors	abstract / PDF
2026-11-05	Decision Models as Retrieval Gates Against Injection and Pollution Mahdi Ghadamyari, Reza Habibi	Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-11-05	Escalate or Close: How Fast-Tier Models Handle Held-Out Web Attack Families in Two-Tier Triage Maciej Kisielewicz, Michał Kędziora, Ngoc Thanh Nguyen	Other LLM Security	abstract / PDF
2026-11-05	KeHoSu: Keyed Homoglyph Substitution for Authenticated Text Provenance over Copy-Paste Channels Andrei Alexandru Drăghici, Sediola Ruko, Briland Hitaj, et al.	Other LLM Security	abstract / PDF
2026-11-05	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, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-11-05	ContractLens: Latent Security Knowledge for Malicious Smart Contract Detection Shuyi Miao, Xinyi Huang, Wangjie Qiu, et al.	Software & Vulnerability Security	abstract / PDF
2026-11-05	Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study Duo Chai, Zizhen Liu, Shuhuai Wang, et al.	Software & Vulnerability Security	abstract / PDF
2026-11-05	CANMentor: A Large-Small Model Collaboration Framework for CAN Bus Intrusion Detection Zhiquan Liu, Haolin Gao, Bo Wu, et al.	Privacy & Data Leakage, Malware, Phishing & Cyber Defense	abstract / PDF
2026-11-05	An Information Bottleneck for Post-hoc Memorization Mitigation in LLMs Dina EL Zein, Shashi Kumar, James Henderson	Privacy & Data Leakage, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-11-05	Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks Rongting Zhang, Martin Bertran, Sandeep Avula, et al.	Prompt Injection & Jailbreaks, Agent & Tool Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-11-05	Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs Seunghyun Lee, Dongyoon Han, Sangdoo Yun	Safety, Alignment & Misuse, Malware, Phishing & Cyber Defense	abstract / PDF
2026-11-05	A Gingerbread House for LLM Agents: Source-Planned Honeypots That Lure Autonomous Attackers into an Isolated Shadow Seungdeok Roh, Seokjun Ryu, Sohee Park, et al.	Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-11-05	JailBound: FOL-Guided Jailbreak Evaluation for Exploring LLM Behavioral Boundaries Fazong Wu, Xin Wang, Ming Yang, et al.	Prompt Injection & Jailbreaks, Safety, Alignment & Misuse, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-11-05	MemForm: Benchmarking Memory Formation Poisoning in LLM Agents Haowen Pan, Pengyang Shao, Yunshan Ma, et al.	Agent & Tool Security, Adversarial ML, Poisoning & Backdoors, 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.