2nd/10_Wiki/Topics/AI_and_ML/Out-of-distribution-Detection.md

---
id: wiki-2026-0508-out-of-distribution-detection
title: Out-of-Distribution Detection
category: 10_Wiki/Topics
status: verified
canonical_id: self
aliases: [OOD-Detection, OOD, Anomaly-Detection-NN, Novelty-Detection]
duplicate_of: none
source_trust_level: A
confidence_score: 0.9
verification_status: applied
tags: [ood, safety, uncertainty, foundation-models, anomaly-detection]
raw_sources: []
last_reinforced: 2026-05-10
github_commit: pending
tech_stack:
  language: python
  framework: pytorch
---

# Out-of-Distribution Detection

## 매 한 줄
> **"매 model 이 본 적 없는 input 의 거부"**. OOD detection 은 inference 시 input 이 training distribution 밖인지 판정하여 silent failure 를 막는 safety layer. 매 2026 의 표준은 foundation-model embedding 위 의 KNN / Mahalanobis 또는 logit-energy score, classical ODIN 은 baseline.

## 매 핵심

### 매 score family
1. **Softmax baseline (MSP)**: max softmax probability — weak baseline.
2. **ODIN** (Liang 2018): temperature scaling + input gradient perturbation.
3. **Energy** (Liu 2020): `-T * logsumexp(logits / T)`, free, strong.
4. **Mahalanobis** (Lee 2018): class-conditional Gaussian on penultimate features.
5. **KNN** (Sun 2022): k-NN distance in feature space — 매 simple, robust.
6. **DOSE / VIM** (2022-2024): residual + logit hybrid.
7. **Foundation-model OOD** (CLIP, DINOv2 features + KNN) — 2026 SOTA.

### 매 evaluation
- AUROC, FPR@95TPR, AUPR.
- ID = CIFAR-10/ImageNet, OOD = SVHN, Textures, iNaturalist, Places, OpenOOD bench.
- **near-OOD** (CIFAR10 vs CIFAR100) 가 매 어려운 case.

### 매 응용
1. autonomous driving 의 unknown object reject.
2. medical imaging 의 unsupported modality flag.
3. LLM 의 jailbreak / off-distribution prompt detection.
4. fraud detection 의 novel attack pattern.

## 💻 패턴

### Energy score (Liu 2020)
```python
import torch, torch.nn.functional as F

@torch.no_grad()
def energy_score(model, x, T=1.0):
    logits = model(x)
    # higher energy = OOD
    return -T * torch.logsumexp(logits / T, dim=-1)
```

### MSP baseline
```python
@torch.no_grad()
def msp(model, x):
    return -F.softmax(model(x), dim=-1).max(-1).values
```

### Mahalanobis on features
```python
@torch.no_grad()
def fit_mahalanobis(features, labels, num_classes):
    means = []
    for c in range(num_classes):
        means.append(features[labels == c].mean(0))
    means = torch.stack(means)
    centered = features - means[labels]
    cov = centered.T @ centered / len(features)
    inv = torch.linalg.pinv(cov)
    return means, inv

def maha_score(f, means, inv):
    diffs = f.unsqueeze(1) - means    # [N, C, D]
    d2 = torch.einsum("ncd,de,nce->nc", diffs, inv, diffs)
    return d2.min(-1).values          # smallest distance to any class
```

### KNN OOD (Sun 2022)
```python
import torch, torch.nn.functional as F

class KNNOOD:
    def __init__(self, k=50):
        self.k = k
    def fit(self, train_feats):
        self.bank = F.normalize(train_feats, dim=-1)
    def score(self, feats):
        f = F.normalize(feats, dim=-1)
        sim = f @ self.bank.T          # cosine
        topk = sim.topk(self.k, dim=-1).values
        return -topk[:, -1]            # negative k-th similarity → OOD score
```

### ODIN
```python
def odin_score(model, x, T=1000, eps=0.0014):
    x = x.clone().detach().requires_grad_(True)
    logits = model(x) / T
    p = F.softmax(logits, dim=-1).max(-1).values
    p.sum().backward()
    x_adv = x - eps * x.grad.sign()
    with torch.no_grad():
        return F.softmax(model(x_adv) / T, dim=-1).max(-1).values
```

### Foundation-model OOD (DINOv2 + KNN)
```python
import torch
dino = torch.hub.load("facebookresearch/dinov2", "dinov2_vitb14").eval().cuda()

@torch.no_grad()
def feats(x):
    return dino(x)   # [B, 768]

knn = KNNOOD(k=50)
knn.fit(feats(train_loader_id))
ood_scores = knn.score(feats(test_batch))
```

### LLM OOD via embedding
```python
from sentence_transformers import SentenceTransformer
emb = SentenceTransformer("BAAI/bge-large-en-v1.5")
id_bank = emb.encode(in_dist_prompts, normalize_embeddings=True)

def prompt_ood(prompt, k=20):
    q = emb.encode([prompt], normalize_embeddings=True)
    sims = (q @ id_bank.T)[0]
    return -sims.topk(k).values.min()
```

### Threshold calibration (FPR@95TPR)
```python
import numpy as np
def threshold_at_tpr(scores_id, tpr=0.95):
    return np.quantile(scores_id, 1 - tpr)
```

## 매 결정 기준
| 상황 | Method |
|---|---|
| 매 simple, 즉시 | Energy |
| 매 best AUROC | KNN on foundation features |
| 매 access to features only | Mahalanobis |
| 매 CV with strong backbone | DINOv2 + KNN |
| 매 LLM input filter | embedding KNN + threshold |
| 매 production, low-latency | Energy or MSP |

**기본값**: foundation embedding + KNN (k=50).

## 🔗 Graph
- 부모: [[Uncertainty-Estimation]] · [[Anomaly-Detection]]
- 변형: [[Energy-Based-Models]] · [[Mahalanobis]] · [[KNN]]
- 응용: [[Safe-Deployment]] · [[Active-Learning]] · [[Open-Set-Recognition]]
- Adjacent: [[Calibration]] · [[Conformal-Prediction]] · [[DINOv2]]

## 🤖 LLM 활용
**언제**: 매 high-stakes deployment, jailbreak filter, novel-prompt routing.
**언제 X**: 매 closed-world benchmark — distribution 가 fixed 인 경우 overhead.

## ❌ 안티패턴
- **MSP only**: 매 over-confident network 에서 거의 무력.
- **Train OOD detector on test OOD set**: leakage, false confidence.
- **Threshold from training scores**: ID validation set 에서 calibrate.
- **Ignore near-OOD**: far-OOD AUROC 99% 인데 near-OOD 60% 인 흔한 함정.
- **Foundation-model embedding mismatch**: ImageNet-pretrained 으로 medical OOD detect.

## 🧪 검증 / 중복
- Verified (OpenOOD benchmark 2024, Sun 2022 KNN, Liu 2020 Energy).
- 신뢰도 A.

## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — Energy/Maha/KNN + foundation-model OOD |