CyberPal 2.0 20B

threat correlation · SOC

IBM Research's security model fine-tuned on enriched cyber chain-of-thought data (SecKnowledge 2.0) over a gpt-oss-20B MoE base.

Context8,192
Curationcurated
AvailabilityAvailable
Price / Mtok$0.15 in · $0.60 out
Basegpt-oss-20b
QuantizationQ4_K_M
LicenseApache-2.0

Source: cyber-pal-security/CyberPal2.0-20B on HuggingFace

Good for
  • +CTI knowledge
  • +threat investigation
  • +vuln correlation
Model cardfrom the published weights — parameters, architecture, training, intended use
Parameters~20B
Architecturegpt-oss 20B (MoE)
Modalitytext
Training

Fine-tuned on SecKnowledge 2.0 chain-of-thought cyber data over gpt-oss-20b (IBM Research, arXiv:2510.14113).

Intended use
  • ›Cyber Threat Intelligence (CTI)
  • ›Vulnerability & weakness analysis
  • ›Detection & mitigation guidance
  • ›Security operations support
Call it from your own codethe API is OpenAI-compatible — an existing client needs one line changed

Your key comes from /keys. Every request is metered and audited against your account, and the model id is the slug in this page’s address.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AD_API_KEY"],
    base_url="https://adversariallm.ai/v1",
)

stream = client.chat.completions.create(
    model="cyberpal-2-20b",
    messages=[{"role": "user", "content": "…"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")
Full model cardcurated from the model's HuggingFace card — description, training, usage, limitations, reported benchmarks

CyberPal-2.0-20B is a cybersecurity-expert 20B-parameter Small Language Model (SLM) fine-tuned from gpt-oss-20b for security operations and threat-management workflows — e.g., cyber threat intelligence (CTI) Q&A, vulnerability-to-weakness mapping, and detection/mitigation recommendations. It is part of the CyberPal 2.0 model family (4B–20B) and is tied to the paper "Toward Cybersecurity-Expert Small Language Models" (arXiv:2510.14113, IBM Research; authors Levi, Ohayon, Blobstein, Sagi, Molloy, Allouche). The card describes it as a decoder-only, instruction-tuned model trained with the SecKnowledge 2.0 data enrichment and formatting pipeline to produce higher-fidelity, task-grounded reasoning traces (chain-of-thought) for cybersecurity tasks. Its stated domain focus spans CTI, SOC/IR, appsec, IAM, and governance/compliance. The card lists an 8192-token context length, BF16 tensors, and Apache-2.0 licensing, and explicitly frames outputs as advisory rather than authoritative.

Training data

Fine-tuned on SecKnowledge 2.0, described by the card as the output of an enrichment + formatting pipeline that: (1) uses expert-in-the-loop schema/format steering (task-specific reasoning formats), (2) performs multi-step grounding using documents and/or web search, and (3) uses LLM-based judging for readability/factuality checks. Per the card, the starting SecKnowledge dataset comprises ~153k instructions in the first stage (from structured public security sources), expanded to a ~403k-example cybersecurity corpus in the second stage via synthetic generation. The SecKnowledge 2.0 pipeline is stated to use gpt-oss-120b (Medium reasoning effort) as the backbone LLM for dataset generation/enrichment. No raw pretraining corpus or full data-source list is enumerated on the card beyond "structured public security sources."

Intended use
  • +Cyber Threat Intelligence (CTI): answering CTI questions; mapping campaigns/actors/techniques; explaining ATT&CK concepts
  • +Vulnerability & weakness analysis: correlating CVE evidence / bug tickets to CWE root causes
  • +Detection & mitigation guidance: proposing detections/mitigations for tactics/techniques/weaknesses/vulnerabilities
  • +Security operations support: incident summarization, investigation assistance, hypothesis-driven triage, response recommendations
Limitations
  • −Out-of-scope: any form of wrongdoing, intrusion, malware development, or instructions intended to enable harm (card explicitly disallows)
  • −Not recommended for high-stakes decisions without human review — the card says to treat outputs as advisory, not authoritative
  • −Agentic / tool use is currently not tested; the card says support will be released in newer versions
  • −No benchmark or evaluation results are provided on the model card itself (performance claims live in the paper, not the card)
  • −No chat template / system-prompt format is documented on the card; usage examples pass a raw prompt string with no chat template applied
Running the weights yourself

The maker’s own snippet, from the model card — it downloads the weights and runs them on your hardware. Kept here because reproducing a result independently is the point, not because you need it to use the model.

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "cyber-pal-security/CyberPal-2.0-20B"

tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

prompt = """Analyze this C code snippet. Identify the vulnerability, the potential impact, and provide a patched version.

void process_data(char *input) {
    char buffer[128];
    strcpy(buffer, input);
    printf("Processed: %s", buffer);
}"""
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    out = model.generate(
        **inputs,
        max_new_tokens=512,
        do_sample=False,
        temperature=0.0,
    )

print(tokenizer.decode(out[0], skip_special_tokens=True))
```
The card also provides a vLLM example (LLM(model=model_id, dtype="bfloat16", tensor_parallel_size=1); SamplingParams(max_tokens=512, temperature=0.0)) and notes that newer vLLM versions should set `export VLLM_USE_FLASHINFER_MOE_FP16=0` to avoid numerical issues.
Scores

No measurements published for this version yet.

Baseline is the strongest general-purpose model we could run on the same suite, same setup, same day. The control row tells you what the other rows are worth.

Versionsscores attach to a version; v2 does not inherit v1's numbers
v12026-08-07—current

Start with CyberPal 2.0 20B

A confirmed email account includes 30 free messages a month.

Sign in to start