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

1912 papers across 4 publication years. Latest arXiv metadata update: 2026-10-16.

Topic	Papers
Prompt Injection & Jailbreaks	437
Agent & Tool Security	470
Privacy & Data Leakage	299
Safety, Alignment & Misuse	453
Adversarial ML, Poisoning & Backdoors	420
Software & Vulnerability Security	576
Malware, Phishing & Cyber Defense	235
Evaluation, Benchmarks & Red Teaming	916
Other LLM Security	124

Latest papers

Updated	Paper	Topics	Links
2026-10-16	HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation Manohar Vellala, Soumya Banerjee, Sandip Roy, et al.	Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-16	ABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics Xiaohang Yu, Hejia Geng, William Knottenbelt	Agent & Tool Security, Adversarial ML, Poisoning & Backdoors, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-16	The Infinite Mutation Engine? Measuring Polymorphism in LLM-Generated Offensive Code Gabriel Hortea, Mario Varlese, Simon Pietro Romano, et al.	Malware, Phishing & Cyber Defense, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-16	From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation Gabriel Hortea, Simon Pietro Romano, Juan Tapiador, et al.	Privacy & Data Leakage, Adversarial ML, Poisoning & Backdoors, Software & Vulnerability Security, Malware, Phishing & Cyber Defense	abstract / PDF
2026-10-16	S-GAP: Stealthy Graph Attack Primitives for Graph Large Language Models Wenda Li, Tongya Zheng, Shunyu Liu, et al.	Agent & Tool Security, Adversarial ML, Poisoning & Backdoors, Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-16	MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection Songping Wang, Peiyang Li, Yi Huang, et al.	Prompt Injection & Jailbreaks, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-16	Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents Farhan Zarif, Kazi Shahid Ahmed Galib, Synthia Akter Promi, et al.	Prompt Injection & Jailbreaks	abstract / PDF
2026-10-16	AgentLoupe: Kernel-Resident Semantic Causal Labels for AI Agent Observability Yifei Bao, Ting Liu, Yuxin Ren, et al.	Other LLM Security	abstract / PDF
2026-10-16	From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images Zhiqing Guo, Lixin Jia, Luning Sun, et al.	Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-16	When Approval Becomes Execution: Authorization-Grounded Workflow Attacks on Tool-Using Agents Chenggong Shi, Hongmei Mou	Agent & Tool Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-16	VulnSAGE: Adjudicating SAST Reports by Connecting LLM Reasoning to Program Structure Jinbao Chen, Zixiang Zhou, Yu Zhang, et al.	Software & Vulnerability Security, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-16	ECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak Attack Yuanwei Wu, Lingdong Huang, Yunlong Mao, et al.	Prompt Injection & Jailbreaks, Safety, Alignment & Misuse, Evaluation, Benchmarks & Red Teaming	abstract / PDF
2026-10-16	Surprise Masking: Private Data Filtering with Model Likelihoods Riya Tyagi, Sahra Ghalebikesabi, Vinnie Monaco, et al.	Privacy & Data Leakage	abstract / PDF
2026-10-16	SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval Haoming Li, Dingyi Kang, Xu Hu, et al.	Agent & Tool Security	abstract / PDF
2026-10-16	When Core-Network Elements Become Reachable: Field-Level Exploitability Analysis in Diameter Wei Yi, Changlong Han, Xue Zhang, 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.