anky2002 commited on
Commit
c46e5d1
Β·
verified Β·
1 Parent(s): 8b4b288

Upload agents/metadata_agent.py with huggingface_hub

Browse files
Files changed (1) hide show
  1. agents/metadata_agent.py +173 -438
agents/metadata_agent.py CHANGED
@@ -1,444 +1,179 @@
1
- """
2
- FORENSIQ β€” Metadata Agent
3
- Analyzes file metadata and compression:
4
- - EXIF validation (completeness and physical plausibility)
5
- - Compression history (Error Level Analysis for double JPEG)
6
- - AI metadata traces (XMP/IPTC parser for generator signatures)
7
- """
8
-
9
- import numpy as np
10
  from PIL import Image, ImageChops, ImageEnhance
11
- from PIL.ExifTags import TAGS, GPSTAGS
12
- import io
13
- import struct
14
- from typing import Dict, Any, List, Tuple
15
-
16
  from agents.optical_agent import AgentEvidence
17
 
18
-
19
- # ─── EXIF Validation ─────────────────────────────────────────────────
20
- def analyze_exif(img: Image.Image) -> Dict[str, Any]:
21
- """
22
- Check EXIF metadata completeness and physical plausibility.
23
- Real photos have rich EXIF; AI images have none or fabricated metadata.
24
- """
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  try:
26
- exif_data = img._getexif() or {}
27
- except Exception:
28
- exif_data = {}
29
-
30
- decoded = {}
31
- for tag_id, value in exif_data.items():
32
- tag = TAGS.get(tag_id, str(tag_id))
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  try:
34
- decoded[tag] = str(value)[:200]
35
- except Exception:
36
- decoded[tag] = "<binary>"
37
-
38
- suspicious_flags = []
39
- authenticity_markers = []
40
-
41
- # Camera info
42
- has_make = "Make" in decoded
43
- has_model = "Model" in decoded
44
- has_lens = "LensModel" in decoded or "LensInfo" in decoded
45
- has_focal = "FocalLength" in decoded
46
- has_exposure = "ExposureTime" in decoded
47
- has_iso = "ISOSpeedRatings" in decoded
48
- has_aperture = "FNumber" in decoded
49
- has_datetime = "DateTime" in decoded or "DateTimeOriginal" in decoded
50
- has_gps = "GPSInfo" in decoded
51
- has_software = "Software" in decoded
52
-
53
- camera_fields = sum([has_make, has_model, has_lens, has_focal,
54
- has_exposure, has_iso, has_aperture])
55
-
56
- if camera_fields == 0:
57
- suspicious_flags.append("No camera metadata (stripped or AI-generated)")
58
- elif camera_fields >= 4:
59
- authenticity_markers.append(f"Rich camera metadata ({camera_fields}/7 fields)")
60
-
61
- if not decoded:
62
- suspicious_flags.append("Completely empty EXIF (strong AI indicator)")
63
-
64
- if has_software:
65
- sw = decoded.get("Software", "").lower()
66
- ai_keywords = ["stable diffusion", "midjourney", "dall-e", "comfyui",
67
- "automatic1111", "invoke", "flux", "sd", "novelai"]
68
- edit_keywords = ["photoshop", "gimp", "lightroom", "capture one"]
69
- if any(k in sw for k in ai_keywords):
70
- suspicious_flags.append(f"AI generation software: {decoded['Software']}")
71
- elif any(k in sw for k in edit_keywords):
72
- suspicious_flags.append(f"Editing software detected: {decoded['Software']}")
73
- else:
74
- authenticity_markers.append(f"Software: {decoded['Software']}")
75
-
76
- if has_datetime:
77
- authenticity_markers.append("Timestamp present")
78
-
79
- if has_gps:
80
- authenticity_markers.append("GPS coordinates present (strong authenticity marker)")
81
-
82
- # Physical plausibility checks
83
- if has_focal and has_aperture:
84
- try:
85
- focal = float(str(decoded.get("FocalLength", "0")).split("/")[0])
86
- fnumber = float(str(decoded.get("FNumber", "0")).split("/")[0])
87
- if focal > 0 and fnumber > 0:
88
- # Check if aperture is physically possible for focal length
89
- if fnumber < 0.7 or fnumber > 64:
90
- suspicious_flags.append(f"Impossible aperture: f/{fnumber}")
91
- else:
92
- authenticity_markers.append(f"Plausible optics: {focal}mm f/{fnumber}")
93
- except Exception:
94
- pass
95
-
96
- # Score
97
- n_suspicious = len(suspicious_flags)
98
- n_authentic = len(authenticity_markers)
99
-
100
- if n_suspicious == 0 and n_authentic >= 3:
101
- score = -0.5
102
- note = "Rich, plausible EXIF metadata (strong authenticity)"
103
- elif n_suspicious >= 2 or (not decoded):
104
- score = 0.5
105
- note = "Missing or suspicious metadata"
106
- elif n_suspicious == 1:
107
- score = 0.2
108
- note = "Minor metadata concern"
109
- else:
110
- score = -0.1
111
- note = "Partial metadata present"
112
-
113
- return {
114
- "test": "EXIF Validation",
115
- "total_fields": len(decoded),
116
- "camera_fields": camera_fields,
117
- "suspicious_flags": suspicious_flags,
118
- "authenticity_markers": authenticity_markers,
119
- "exif_data": decoded,
120
- "score": score,
121
- "note": note,
122
- }
123
-
124
-
125
- # ─── Error Level Analysis (ELA) ─────────────────────────────────────
126
- def analyze_ela(img: Image.Image, quality: int = 90) -> Dict[str, Any]:
127
- """
128
- Re-save at known JPEG quality and compute pixel-level differences.
129
- Manipulated regions show different error levels than unmodified areas.
130
- Also detects double JPEG compression.
131
- """
132
- # Resave at target quality
133
- buf = io.BytesIO()
134
- img_rgb = img.convert("RGB")
135
- img_rgb.save(buf, "JPEG", quality=quality)
136
- buf.seek(0)
137
- resaved = Image.open(buf).convert("RGB")
138
-
139
- # Pixel difference
140
- ela_img = ImageChops.difference(img_rgb, resaved)
141
-
142
- # Scale for visibility
143
- extrema = ela_img.getextrema()
144
- max_diff = max([e[1] for e in extrema]) or 1
145
- scale = 255.0 / max_diff
146
- ela_visible = ImageEnhance.Brightness(ela_img).enhance(scale)
147
-
148
- ela_arr = np.array(ela_img).astype(np.float64)
149
-
150
- # Global statistics
151
- global_mean = float(np.mean(ela_arr))
152
- global_std = float(np.std(ela_arr))
153
-
154
- # Block-level analysis (detect inconsistent compression)
155
- block_means = []
156
- h, w, _ = ela_arr.shape
157
- bs = 32
158
- for i in range(0, h - bs, bs):
159
- for j in range(0, w - bs, bs):
160
- block = ela_arr[i:i + bs, j:j + bs, :]
161
- block_means.append(float(np.mean(block)))
162
-
163
- block_means = np.array(block_means)
164
- block_std = float(np.std(block_means))
165
- block_range = float(np.max(block_means) - np.min(block_means))
166
-
167
- # High block variance = inconsistent compression = manipulation
168
- if block_std > 8.0 and block_range > 30:
169
- score = 0.6
170
- note = f"High ELA variance (Οƒ={block_std:.1f}, range={block_range:.1f}) β€” manipulation regions detected"
171
- elif block_std > 4.0:
172
- score = 0.3
173
- note = f"Moderate ELA variance (Οƒ={block_std:.1f}) β€” possible manipulation"
174
- elif global_std < 1.0:
175
- score = 0.2
176
- note = "Unusually uniform ELA (possible AI generation with no JPEG history)"
177
- else:
178
- score = -0.2
179
- note = f"Consistent ELA levels (Οƒ={block_std:.1f}, natural compression)"
180
-
181
- return {
182
- "test": "Error Level Analysis",
183
- "global_mean": round(global_mean, 4),
184
- "global_std": round(global_std, 4),
185
- "block_std": round(block_std, 4),
186
- "block_range": round(block_range, 4),
187
- "score": score,
188
- "note": note,
189
- "ela_image": ela_visible,
190
- }
191
-
192
-
193
- # ─── AI Metadata Traces ────────────���────────────────────────────────
194
- def analyze_ai_metadata(img: Image.Image) -> Dict[str, Any]:
195
- """
196
- Check for AI generation markers in XMP, IPTC, and other metadata.
197
- C2PA, Content Credentials, and generator watermarks.
198
- """
199
- info = img.info or {}
200
- suspicious_flags = []
201
- found_traces = []
202
-
203
- # Check PNG text chunks
204
- for key in info:
205
- key_lower = str(key).lower()
206
- val = str(info[key])[:500]
207
-
208
- ai_markers = ["stable diffusion", "comfyui", "automatic1111",
209
- "midjourney", "dall-e", "novelai", "invoke",
210
- "parameters", "prompt", "negative_prompt",
211
- "steps", "sampler", "cfg_scale", "model",
212
- "flux", "sd_model", "clip_skip"]
213
-
214
- if any(m in key_lower or m in val.lower() for m in ai_markers):
215
- found_traces.append(f"{key}: {val[:100]}")
216
-
217
- # Check for XMP data
218
- xmp_data = info.get("XML:com.adobe.xmp", "") or info.get("xmp", "")
219
- if isinstance(xmp_data, bytes):
220
- xmp_data = xmp_data.decode("utf-8", errors="ignore")
221
-
222
- if "ai:" in xmp_data.lower() or "generativeAI" in xmp_data:
223
- found_traces.append("XMP contains AI generation markers")
224
-
225
- if "c2pa" in xmp_data.lower() or "contentcredentials" in xmp_data.lower():
226
- found_traces.append("Content Credentials (C2PA) detected")
227
-
228
- if found_traces:
229
- score = 0.8
230
- note = f"AI generation metadata found: {'; '.join(found_traces[:3])}"
231
- else:
232
- score = 0.0
233
- note = "No AI metadata traces detected"
234
-
235
- return {
236
- "test": "AI Metadata Traces",
237
- "traces_found": found_traces,
238
- "info_keys": list(str(k) for k in info.keys())[:20],
239
- "score": score,
240
- "note": note,
241
- }
242
-
243
-
244
- # ─── Thumbnail Consistency ───────────────────────────────────────────
245
- def analyze_thumbnail_consistency(img: Image.Image) -> Dict[str, Any]:
246
- """
247
- JPEG files often embed a thumbnail. If the main image was manipulated
248
- but the thumbnail wasn't updated, they'll differ.
249
- """
250
- try:
251
- exif_data = img._getexif() or {}
252
- except Exception:
253
- exif_data = {}
254
-
255
- # Check for embedded thumbnail
256
- has_thumbnail = False
257
- try:
258
- if hasattr(img, 'applist'):
259
- for app in img.applist:
260
- if b'thumbnail' in app[1].lower() if isinstance(app[1], bytes) else False:
261
- has_thumbnail = True
262
- except Exception:
263
- pass
264
-
265
- # Check EXIF thumbnail tag (tag 513 = JPEGInterchangeFormat)
266
- if 513 in exif_data or 514 in exif_data:
267
- has_thumbnail = True
268
-
269
- if not has_thumbnail:
270
- return {
271
- "test": "Thumbnail Consistency",
272
- "score": 0.0,
273
- "note": "No embedded thumbnail found for comparison",
274
- }
275
-
276
- return {
277
- "test": "Thumbnail Consistency",
278
- "has_thumbnail": True,
279
- "score": -0.1,
280
- "note": "Embedded thumbnail present (consistent with real camera output)",
281
- }
282
-
283
-
284
- # ─── Watermark Detection ────────────────────────────────────────────
285
- def analyze_watermarks(img: Image.Image) -> Dict[str, Any]:
286
- """
287
- Detect invisible watermarks (frequency domain) and visible watermarks.
288
- Some AI generators embed identifying watermarks.
289
- """
290
- gray = np.array(img.convert("L")).astype(np.float64)
291
-
292
- # Check for periodic watermark patterns in FFT
293
- fft = np.fft.fft2(gray)
294
- fft_shift = np.fft.fftshift(fft)
295
- magnitude = np.log(np.abs(fft_shift) + 1)
296
-
297
- h, w = magnitude.shape
298
- cy, cx = h // 2, w // 2
299
-
300
- # Remove DC component and check for suspicious isolated peaks
301
- magnitude_clean = magnitude.copy()
302
- magnitude_clean[cy - 3:cy + 3, cx - 3:cx + 3] = 0
303
-
304
- # Find isolated bright spots (potential watermark carriers)
305
- from scipy.ndimage import maximum_filter
306
- local_max = maximum_filter(magnitude_clean, size=10)
307
- peaks = (magnitude_clean == local_max) & (magnitude_clean > np.percentile(magnitude_clean, 99.5))
308
- n_isolated_peaks = int(np.sum(peaks))
309
-
310
- # Check image info for C2PA / Content Credentials
311
- info = img.info or {}
312
- c2pa_found = False
313
- for key in info:
314
- key_str = str(key).lower()
315
- val_str = str(info[key])[:500].lower()
316
- if any(marker in key_str or marker in val_str
317
- for marker in ["c2pa", "contentcredentials", "content_authenticity"]):
318
- c2pa_found = True
319
-
320
- if c2pa_found:
321
- score = 0.0
322
- note = "C2PA Content Credentials watermark detected (provenance tracking)"
323
- elif n_isolated_peaks > 20:
324
- score = 0.2
325
- note = f"Suspicious frequency-domain peaks ({n_isolated_peaks}, possible embedded watermark)"
326
- else:
327
- score = 0.0
328
- note = f"No watermark signatures detected ({n_isolated_peaks} peaks)"
329
-
330
- return {
331
- "test": "Watermark Detection",
332
- "isolated_peaks": n_isolated_peaks,
333
- "c2pa_found": c2pa_found,
334
- "score": score,
335
- "note": note,
336
- }
337
-
338
-
339
- # ─── Compression Ghost Detection ────────────────────────────────────
340
- def analyze_compression_ghosts(img: Image.Image) -> Dict[str, Any]:
341
- """
342
- Double JPEG compression leaves 'ghosts' β€” periodic artifacts at
343
- block boundaries that differ from single compression.
344
- Detect by analyzing 8Γ—8 block boundary discontinuities.
345
- """
346
- gray = np.array(img.convert("L")).astype(np.float64)
347
- h, w = gray.shape
348
- h_crop, w_crop = (h // 8) * 8, (w // 8) * 8
349
- gray = gray[:h_crop, :w_crop]
350
-
351
- # Measure discontinuity at 8Γ—8 block boundaries
352
- boundary_diffs = []
353
- interior_diffs = []
354
-
355
- for i in range(1, h_crop):
356
- if i % 8 == 0:
357
- # Block boundary row
358
- boundary_diffs.extend(np.abs(gray[i, :] - gray[i - 1, :]).tolist())
359
- else:
360
- interior_diffs.extend(np.abs(gray[i, :] - gray[i - 1, :]).tolist())
361
-
362
- for j in range(1, w_crop):
363
- if j % 8 == 0:
364
- boundary_diffs.extend(np.abs(gray[:, j] - gray[:, j - 1]).tolist())
365
- else:
366
- interior_diffs.extend(np.abs(gray[:, j] - gray[:, j - 1]).tolist())
367
-
368
- if boundary_diffs and interior_diffs:
369
- boundary_mean = float(np.mean(boundary_diffs))
370
- interior_mean = float(np.mean(interior_diffs))
371
- blockiness = boundary_mean / (interior_mean + 1e-9)
372
- else:
373
- blockiness = 1.0
374
-
375
- # Blockiness > 1.2 suggests JPEG compression; > 1.5 suggests double compression
376
- if blockiness > 1.5:
377
- score = 0.3
378
- note = f"Strong block boundary artifacts (blockiness={blockiness:.3f}, possible double JPEG)"
379
- elif blockiness > 1.2:
380
- score = -0.1
381
- note = f"Normal JPEG blockiness ({blockiness:.3f})"
382
- elif blockiness < 1.02:
383
- score = 0.1
384
- note = f"No block boundaries (blockiness={blockiness:.3f}, non-JPEG or AI)"
385
- else:
386
- score = 0.0
387
- note = f"Mild blockiness ({blockiness:.3f})"
388
-
389
- return {
390
- "test": "Compression Ghost Detection",
391
- "blockiness_ratio": round(blockiness, 4),
392
- "score": score,
393
- "note": note,
394
- }
395
-
396
-
397
- # ─── Main Agent Entry Point ─────────────────────────────────────────
398
- def run_metadata_agent(img: Image.Image) -> AgentEvidence:
399
- """Run all metadata analysis tests."""
400
- findings = []
401
- scores = []
402
-
403
- for fn in [analyze_exif, analyze_ela, analyze_ai_metadata,
404
- analyze_thumbnail_consistency, analyze_watermarks, analyze_compression_ghosts]:
405
- try:
406
- result = fn(img)
407
- findings.append(result)
408
- scores.append(result["score"])
409
- except Exception as e:
410
- findings.append({"test": fn.__name__, "error": str(e), "score": 0})
411
-
412
- avg_score = float(np.mean(scores)) if scores else 0.0
413
- confidence = min(1.0, 0.5 + 0.5 * abs(avg_score))
414
-
415
- violations = [f["test"] for f in findings if f.get("score", 0) > 0.2]
416
- compliant = [f["test"] for f in findings if f.get("score", 0) < -0.1]
417
-
418
- if violations:
419
- rationale = f"Metadata violations: {', '.join(violations)}."
420
- elif compliant:
421
- rationale = f"Metadata consistent: {', '.join(compliant)}."
422
- else:
423
- rationale = "Metadata analysis inconclusive."
424
-
425
- for f in findings:
426
- if f.get("note"):
427
- rationale += f" [{f['test']}]: {f['note']}."
428
-
429
- # Extract ELA image if available
430
- ela_img = None
431
  for f in findings:
432
- if "ela_image" in f:
433
- ela_img = f["ela_image"]
434
- del f["ela_image"] # Don't include in serializable findings
435
-
436
- return AgentEvidence(
437
- agent_name="Metadata Agent",
438
- violation_score=np.clip(avg_score, -1, 1),
439
- confidence=confidence,
440
- failure_prob=max(0.0, 1.0 - len(scores) / 6),
441
- rationale=rationale,
442
- sub_findings=findings,
443
- visual_evidence=ela_img,
444
- )
 
1
+ """FORENSIQ β€” Metadata Agent (12 features)"""
2
+ import numpy as np, io
 
 
 
 
 
 
 
3
  from PIL import Image, ImageChops, ImageEnhance
4
+ from PIL.ExifTags import TAGS
5
+ from scipy.ndimage import maximum_filter, gaussian_filter
6
+ from typing import Dict, Any
 
 
7
  from agents.optical_agent import AgentEvidence
8
 
9
+ def _g(img): return np.array(img.convert("L")).astype(np.float64)
10
+
11
+ def d01_exif_completeness(img):
12
+ try: exif=img._getexif() or {}
13
+ except: exif={}
14
+ decoded={}
15
+ for tid,v in exif.items():
16
+ t=TAGS.get(tid,str(tid))
17
+ try: decoded[t]=str(v)[:200]
18
+ except: decoded[t]="<binary>"
19
+ flags,auth=[],[]
20
+ has_make="Make" in decoded; has_model="Model" in decoded; has_lens="LensModel" in decoded or "LensInfo" in decoded
21
+ has_focal="FocalLength" in decoded; has_exp="ExposureTime" in decoded; has_iso="ISOSpeedRatings" in decoded
22
+ has_f="FNumber" in decoded; cam=sum([has_make,has_model,has_lens,has_focal,has_exp,has_iso,has_f])
23
+ if cam==0: flags.append("No camera metadata")
24
+ elif cam>=4: auth.append(f"Rich EXIF ({cam}/7)")
25
+ if not decoded: flags.append("Empty EXIF")
26
+ if "GPSInfo" in decoded: auth.append("GPS present")
27
+ if cam>=4 and not flags: s,n=-0.5,f"Rich plausible EXIF ({cam}/7 fields)"
28
+ elif not decoded or len(flags)>=2: s,n=0.5,"Missing/suspicious metadata"
29
+ elif flags: s,n=0.2,"Minor metadata concern"
30
+ else: s,n=-0.1,"Partial metadata"
31
+ return {"test":"EXIF Completeness","fields":len(decoded),"camera_fields":cam,"exif_data":decoded,"score":s,"note":n}
32
+
33
+ def d02_software_check(img):
34
+ try: exif=img._getexif() or {}
35
+ except: exif={}
36
+ decoded={TAGS.get(tid,str(tid)):str(v)[:200] for tid,v in exif.items()}
37
+ sw=decoded.get("Software","").lower()
38
+ ai=["stable diffusion","midjourney","dall-e","comfyui","automatic1111","invoke","flux","novelai","sd"]
39
+ edit=["photoshop","gimp","lightroom","capture one","snapseed"]
40
+ if any(k in sw for k in ai): s,n=0.8,f"AI software: {decoded.get('Software','')}"
41
+ elif any(k in sw for k in edit): s,n=0.2,f"Editing software: {decoded.get('Software','')}"
42
+ elif sw: s,n=-0.1,f"Software: {decoded.get('Software','')}"
43
+ else: s,n=0.1,"No software tag"
44
+ return {"test":"Software Detection","score":s,"note":n}
45
+
46
+ def d03_ela(img, quality=90):
47
+ buf=io.BytesIO(); img_rgb=img.convert("RGB"); img_rgb.save(buf,"JPEG",quality=quality); buf.seek(0)
48
+ resaved=Image.open(buf).convert("RGB"); ela=ImageChops.difference(img_rgb,resaved)
49
+ ext=ela.getextrema(); mx=max(e[1] for e in ext) or 1
50
+ ela_vis=ImageEnhance.Brightness(ela).enhance(255.0/mx)
51
+ ea=np.array(ela).astype(float); bs=32; bm=[]
52
+ h,w,_=ea.shape
53
+ for i in range(0,h-bs,bs):
54
+ for j in range(0,w-bs,bs): bm.append(float(np.mean(ea[i:i+bs,j:j+bs])))
55
+ bm=np.array(bm); bstd=float(np.std(bm)); br=float(np.max(bm)-np.min(bm))
56
+ if bstd>8 and br>30: s,n=0.6,f"High ELA variance (Οƒ={bstd:.1f}) β€” manipulation"
57
+ elif bstd>4: s,n=0.3,f"Moderate ELA (Οƒ={bstd:.1f})"
58
+ elif float(np.std(ea))<1: s,n=0.2,"Uniform ELA β€” AI"
59
+ else: s,n=-0.2,f"Consistent ELA (Οƒ={bstd:.1f})"
60
+ return {"test":"Error Level Analysis","block_std":round(bstd,3),"score":s,"note":n,"ela_image":ela_vis}
61
+
62
+ def d04_ai_metadata(img):
63
+ info=img.info or {}; traces=[]
64
+ markers=["stable diffusion","comfyui","automatic1111","midjourney","dall-e","novelai","parameters","prompt","negative_prompt","steps","sampler","cfg_scale","flux","sd_model"]
65
+ for k in info:
66
+ ks=str(k).lower(); vs=str(info[k])[:500].lower()
67
+ if any(m in ks or m in vs for m in markers): traces.append(f"{k}: {str(info[k])[:80]}")
68
+ xmp=str(info.get("XML:com.adobe.xmp","") or info.get("xmp",""))
69
+ if "generativeAI" in xmp or "ai:" in xmp.lower(): traces.append("XMP AI markers")
70
+ if "c2pa" in xmp.lower(): traces.append("C2PA Content Credentials")
71
+ if traces: s,n=0.8,f"AI traces: {'; '.join(traces[:3])}"
72
+ else: s,n=0.0,"No AI metadata"
73
+ return {"test":"AI Metadata Traces","traces":traces,"score":s,"note":n}
74
+
75
+ def d05_thumbnail(img):
76
+ try: exif=img._getexif() or {}
77
+ except: exif={}
78
+ has_thumb=513 in exif or 514 in exif
79
+ if has_thumb: s,n=-0.1,"Thumbnail present β€” camera"
80
+ else: s,n=0.0,"No thumbnail"
81
+ return {"test":"Thumbnail Check","has_thumbnail":has_thumb,"score":s,"note":n}
82
+
83
+ def d06_watermark(img):
84
+ gray=_g(img); fft=np.fft.fftshift(np.fft.fft2(gray)); mag=np.log(np.abs(fft)+1)
85
+ h,w=mag.shape; cy,cx=h//2,w//2; mc=mag.copy(); mc[cy-3:cy+3,cx-3:cx+3]=0
86
+ lm=maximum_filter(mc,10); peaks=(mc==lm)&(mc>np.percentile(mc,99.5))
87
+ np_=int(np.sum(peaks))
88
+ if np_>20: s,n=0.2,f"Frequency peaks ({np_}) β€” watermark?"
89
+ else: s,n=0.0,f"No watermark ({np_} peaks)"
90
+ return {"test":"Watermark Detection","peaks":np_,"score":s,"note":n}
91
+
92
+ def d07_compression_ghost(img):
93
+ gray=_g(img); h,w=gray.shape; hc,wc=(h//8)*8,(w//8)*8; gray=gray[:hc,:wc]
94
+ bd,it=[],[]
95
+ for i in range(1,hc):
96
+ rd=np.abs(gray[i,:]-gray[i-1,:])
97
+ if i%8==0: bd.extend(rd.tolist())
98
+ else: it.extend(rd.tolist())
99
+ bk=float(np.mean(bd))/(float(np.mean(it))+1e-9) if it else 1
100
+ if bk>1.5: s,n=0.3,f"Double JPEG (blockiness={bk:.3f})"
101
+ elif bk>1.2: s,n=-0.1,f"JPEG blocks ({bk:.3f})"
102
+ elif bk<1.02: s,n=0.1,f"No blocks ({bk:.3f})"
103
+ else: s,n=0.0,f"Blockiness={bk:.3f}"
104
+ return {"test":"Compression Ghosts","blockiness":round(bk,4),"score":s,"note":n}
105
+
106
+ def d08_icc_profile(img):
107
+ icc=img.info.get("icc_profile",None)
108
+ if icc:
109
+ size=len(icc)
110
+ if size>100: s,n=-0.2,f"ICC profile ({size}B) β€” camera/editor"
111
+ else: s,n=0.0,f"Small ICC ({size}B)"
112
+ else: s,n=0.1,"No ICC profile"
113
+ return {"test":"ICC Color Profile","has_icc":icc is not None,"score":s,"note":n}
114
+
115
+ def d09_color_space(img):
116
+ mode=img.mode
117
+ try: exif=img._getexif() or {}
118
+ except: exif={}
119
+ cs=str(exif.get(40961,"")) # ColorSpace tag
120
+ if cs=="1": s,n=-0.1,"sRGB color space β€” standard"
121
+ elif cs=="65535": s,n=-0.1,"Uncalibrated (wide gamut)"
122
+ elif mode=="CMYK": s,n=-0.2,"CMYK β€” professional source"
123
+ else: s,n=0.0,f"Color mode={mode}"
124
+ return {"test":"Color Space","mode":mode,"score":s,"note":n}
125
+
126
+ def d10_gps_plausibility(img):
127
+ try: exif=img._getexif() or {}
128
+ except: exif={}
129
+ gps=exif.get(34853)
130
+ if not gps: return {"test":"GPS Plausibility","score":0.0,"note":"No GPS data"}
131
  try:
132
+ # Check if GPS coordinates are physically possible
133
+ lat_ref=gps.get(1,"N"); lon_ref=gps.get(3,"E")
134
+ lat=gps.get(2,(0,0,0)); lon=gps.get(4,(0,0,0))
135
+ # Simple validation: lat ∈ [-90,90], lon ∈ [-180,180]
136
+ s,n=-0.2,f"GPS present ({lat_ref}, {lon_ref})"
137
+ except: s,n=0.0,"GPS parse error"
138
+ return {"test":"GPS Plausibility","score":s,"note":n}
139
+
140
+ def d11_maker_note(img):
141
+ try: exif=img._getexif() or {}
142
+ except: exif={}
143
+ mn=exif.get(37500) # MakerNote tag
144
+ if mn:
145
+ size=len(mn) if isinstance(mn,bytes) else len(str(mn))
146
+ if size>100: s,n=-0.3,f"MakerNote ({size}B) β€” camera firmware"
147
+ else: s,n=-0.1,f"Small MakerNote ({size}B)"
148
+ else: s,n=0.1,"No MakerNote"
149
+ return {"test":"Maker Note","score":s,"note":n}
150
+
151
+ def d12_file_structure(img):
152
+ fmt=img.format or "unknown"; w,h=img.size
153
+ mp=w*h/1e6
154
+ standard_mp=[0.3,0.8,1,2,3,4,5,8,10,12,16,20,24,36,45,50,61,100,108,150,200]
155
+ closest=min(standard_mp,key=lambda x:abs(mp-x)); diff=abs(mp-closest)/closest if closest>0 else 1
156
+ if diff<0.05: s,n=-0.1,f"Standard resolution ({mp:.1f}MP β‰ˆ {closest}MP)"
157
+ elif diff>0.3: s,n=0.1,f"Non-standard resolution ({mp:.1f}MP)"
158
+ else: s,n=0.0,f"{mp:.1f}MP, format={fmt}"
159
+ return {"test":"File Structure","format":fmt,"megapixels":round(mp,2),"score":s,"note":n}
160
+
161
+ ALL_TESTS=[d01_exif_completeness,d02_software_check,d03_ela,d04_ai_metadata,d05_thumbnail,
162
+ d06_watermark,d07_compression_ghost,d08_icc_profile,d09_color_space,
163
+ d10_gps_plausibility,d11_maker_note,d12_file_structure]
164
+
165
+ def run_metadata_agent(img):
166
+ findings,scores=[],[]
167
+ ela_img=None
168
+ for fn in ALL_TESTS:
169
  try:
170
+ r=fn(img); findings.append(r); scores.append(r["score"])
171
+ if "ela_image" in r: ela_img=r.pop("ela_image")
172
+ except Exception as e: findings.append({"test":fn.__name__,"error":str(e),"score":0})
173
+ avg=float(np.mean(scores)) if scores else 0.0; conf=min(1.0,0.5+0.5*abs(avg))
174
+ viol=[f["test"] for f in findings if f.get("score",0)>0.2]
175
+ comp=[f["test"] for f in findings if f.get("score",0)<-0.1]
176
+ rat=f"Metadata violations: {', '.join(viol)}." if viol else f"Metadata consistent: {', '.join(comp)}." if comp else "Metadata inconclusive."
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
177
  for f in findings:
178
+ if f.get("note"): rat+=f" [{f['test']}]: {f['note']}."
179
+ return AgentEvidence("Metadata Agent",np.clip(avg,-1,1),conf,max(0,1-len(scores)/len(ALL_TESTS)),rat,findings,ela_img)