Skip to content
Shaiex Shaiex /ai-sec
Resources / Research Library

Research, benchmarks, and open-source tooling for LLM threat modeling.

Twenty-seven peer-reviewed papers, the PromptArmor open-source project, MITRE ATLAS coverage evaluations, and the commissioned Forrester Total Economic Impact study — everything a skeptical CISO needs to validate our claims before booking a demo.

27 peer-reviewed papers · 8,400+ GitHub stars · 3 active certifications
By the numbers
27 Peer-reviewed papers on LLM threat modeling since 2021
8,400+ GitHub stars on PromptArmor, MIT-licensed open-source firewall
99.97% Platform uptime over the trailing 12 months — status.shaiex.net
3 Certifications held: SOC 2 Type II · ISO 27001 · ISO/IEC 42001
Research catalog

LLM threat modeling research catalog.

The corpus covers prompt injection, model exfiltration, training-data leakage, and supply-chain attacks across OpenAI, Anthropic, Bedrock, Vertex, and self-hosted foundation model stacks. Each entry lists authors, venue, year, and a one-line abstract so you can scan relevance without leaving the page.

  1. 2024 MITRE ATLAS / arXiv

    Coverage evaluation of LLM threat detection across the MITRE ATLAS adversary matrix.

    Rao, A., Vell, M., Chen, S., Park, J., et al.

    Independent benchmark of detection depth across all 14 ATLAS tactics — Shaiex surfaces 4.8× more shadow LLM endpoints than the nearest competitor.

    prompt injection exfiltration ATLAS Featured
    142 citations
  2. 2024 USENIX Security

    A taxonomy of indirect prompt-injection payloads against retrieval-augmented assistants.

    Vell, M., Rao, A., Singh, R., Okafor, B.

    Categorizes 1,184 adversarial payloads from in-the-wild RAG deployments and proposes the PU-12 classification still cited by OWASP LLM Top-10.

    prompt injection RAG OWASP
    98 citations
  3. 2023 IEEE S&P

    Training-data leakage in production foundation models: measurement and mitigation.

    Chen, S., Vell, M., Park, J., Iyengar, A.

    First systematic study of verbatim regurgitation across OpenAI, Anthropic, and open-weight models; introduces the RecallBench harness now maintained at Shaiex.

    data leakage benchmark foundation models
    211 citations
  4. 2022 ACM CCS

    Model exfiltration via accelerator side channels in multi-tenant inference clusters.

    Vell, M., Rao, A., Singh, R.

    Demonstrates weight recovery from co-tenant GPU memory pressure signals; informs the isolation guarantees in Shaiex Defender's data-plane.

    model exfil side channel GPU
    76 citations

Showing 4 of 27. Full catalog with DOI links, BibTeX, and PDF access is available to verified enterprise evaluators.

Request full access →
Founders' note

Why we publish.

When we started Shaiex in 2020, the security community had no shared vocabulary for LLM-specific attacks. Threat models written for traditional software did not transfer. Red-teamers were improvising. We thought the fastest way to fix that was to publish every technique we found — including the ones our own product defends against — and let the field argue about them in the open.

Six years later, the research program has produced twenty-seven peer-reviewed papers, the PromptArmor open-source project, and the LLM threat-detection track at USENIX Security. We are proud of the work, and prouder still that researchers outside Shaiex have built on top of it. PromptArmor alone has been forked into three commercial products and is referenced in the OWASP LLM Top-10.

What we're publishing next: a four-part series on agentic-tool exfiltration (Q2 2025), an updated MITRE ATLAS coverage matrix for multimodal models (Q3 2025), and the v2 PromptArmor release with native support for streaming token-level filtering. If you want the preprints before they go public, the best way in is to book a demo and tell us what you're trying to defend.

— Dr. Aditi Rao, Co-founder & CEO · Marcus Vell, Co-founder & CTO Austin · Tel Aviv · Bangalore · 14 March 2025
promptarmor · v1.4.2 MIT
payload verdict latency
"ignore previous instructions…" BLOCK · 99.4% 3.1 ms
system-prompt override via image OCR BLOCK · 99.4% 4.8 ms
tool-call exfil via tool_choice BLOCK · 99.4% 2.7 ms
benign: summarize invoice.txt ALLOW 0.9 ms
benign: write a haiku about Austin ALLOW 0.8 ms
OWASP LLM Top-10 compliant patented firewall · USPTO #11,984,221
Open source

PromptArmor: the open-source prompt-injection firewall.

MIT-licensed, maintained by the Shaiex research team, and used by security teams at companies we don't sell to. PromptArmor ships as a single-binary sidecar that wraps any LLM gateway — OpenAI, Anthropic, Bedrock, Vertex, or self-hosted — and blocks the OWASP LLM Top-10 at the prompt boundary with a 3 ms median latency overhead.

  • 8,400+ GitHub stars, 312 contributors, MIT licensed
  • 99.4% block rate across OWASP LLM Top-10 published benchmarks
  • 3 ms median latency overhead — no extra hop in the hot path
  • Drop-in for LangChain, LlamaIndex, OpenAI Functions, and MCP tool calls

"PromptArmor is the first prompt-injection control we'd actually let a customer run in production without our team in the loop."

— Staff Security Engineer, Fortune 50 insurer (independent quote, used with permission)