bert-log-anomaly-detection

def predict_log(log_text):
    log_text = add_prefix_token(log_text)
    inputs = tokenizer(
        log_text,
        return_tensors="pt",
        truncation=True,
        padding=True, # for cases when the inference contains more than 1 log, i.e., batch size > 1
        max_length=128
    )

    with torch.no_grad():
        logits = model(**inputs).logits
        pred = torch.argmax(logits, dim=1).item()
        prob = torch.softmax(logits, dim=-1).tolist()[0]

    return "Normal" if pred == 1 else "Anomaly", prob

# Example 1
text1 = "SELECT * FROM users WHERE id = 1 OR 1=1"
print(predict_log(text1))

# Example 2
text2 = "2025-01-06 14:23:45 | User: anonymous | IP: 203.154.89.102 | Duration: 0.05s SELECT * FROM users WHERE username = 'admin' OR '1'='1' -- ' AND password = 'x'"
print(predict_log(text2))

# Example 3
text3 = "3051-06-22T07:20:02.296945Z 3 Query select e3mJKDCCY from 7Q8SpG8LLEWhrfpe4s5 where ph4d = 'a1S9hQa92uC1EAyJf2Y';"
print(predict_log(text3))