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

1881 papers across 4 publication years. Latest arXiv metadata update: 2026-10-15.

Topic	Papers
Prompt Injection & Jailbreaks	427
Agent & Tool Security	462
Privacy & Data Leakage	293
Safety, Alignment & Misuse	448
Adversarial ML, Poisoning & Backdoors	412
Software & Vulnerability Security	570
Malware, Phishing & Cyber Defense	231
Evaluation, Benchmarks & Red Teaming	900
Other LLM Security	123

Latest papers

Updated	Paper	Topics	Links
2026-10-15	Private Retrieval Augmented Generation via Random Projection Dixi Yao, Tahseen Rabbani, Tian Li	Privacy & Data Leakage	abstract / PDF
2026-10-15	Autonomous OSS Threat Detection via Taxonomy-Aligned LLMs Md. Robiul Islam Niloy	Safety, Alignment & Misuse, Adversarial ML, Poisoning & Backdoors, Malware, Phishing & Cyber Defense, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-15	PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents Kshitij Mishra, Abhijith Sharma, Nils Lukas, et al.	Agent & Tool Security, Privacy & Data Leakage, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-15	SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes Mengxiao Wang, Nitesh Saxena	Agent & Tool Security, Adversarial ML, Poisoning & Backdoors, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-15	Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection Asif Shahriar, Hongyu Cai, Hadjer Benkraouda, et al.	Software & Vulnerability Security	abstract / PDF
2026-10-15	Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems Linda Beková, Rodrigo Alves	Privacy & Data Leakage, Safety, Alignment & Misuse	abstract / PDF
2026-10-15	From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents Yiqi Wang, Jiaqi Zhang, Zhangkai Wu, et al.	Agent & Tool Security, Privacy & Data Leakage, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-15	SecureClaw: Clawing Back Control of LLM Agents Yuhan Ma, Stefan Schmid	Agent & Tool Security	abstract / PDF
2026-10-15	BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition Zhiyuan Wang, Yuezhi Zhou, Ziqi Zhang, et al.	Privacy & Data Leakage, Software & Vulnerability Security	abstract / PDF
2026-10-15	On the Privacy of LLMs: An Ablation Study Karima Makhlouf, Lamiaa Basyoni, Syed Khaderi, et al.	Privacy & Data Leakage, Adversarial ML, Poisoning & Backdoors, Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-15	Poisoning the Neighborhood: A Topology-Aware Topic-Level Attack on Large-Scale HNSW-based RAG Systems Yufei Chen, Yao Wang, Haibin Zhang	Adversarial ML, Poisoning & Backdoors	abstract / PDF
2026-10-15	What Survives Self-Evolution: Provenance Marks in Copied Agent Harnesses Jieyu Li, Jingya Li, Sheng Li, et al.	Other LLM Security	abstract / PDF
2026-10-15	Evaluating and Improving Static Application Security Testing Tools for Rust Huaien Zhang, Zhengjie Zhao, Yu Pei, et al.	Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-15	QuasiLeak-Bench: Evaluating LLM-Based Privacy Detectors on Policy-Conditioned Quasi-Evidence Group Recovery Yufan Zhu, Yangfan Jiang, Yang Fei, et al.	Privacy & Data Leakage, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-15	Combining LLM and Dynamic Analysis for Universal Testing of Static Application Security Testing Tools Huaien Zhang, Yu Pei, Hao Chen, et al.	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.