BookNotesSlidesP-sets Syllabusdraft · v0.2.49.1
💬Comments welcome. To leave a note, select any text and click the note / highlight button that pops up — or open the panel with the tab at the top-right (‹). Notes are visible only inside our private review group.
Computational Photography, an AI-powered Slopendium — 41 Image Forensics and Authentication
expand to📖 Full book outline1 parts · 2 chapters · 9 sections · 11 figures embedded · 4 placeholders · double-click a figure to enlarge
▸Part 41 IMAGE FORENSICS AND AUTHENTICATION⧉
<!--uid: image-forensics-and-authentication-->
The rest of this book is mostly about *making* images — better, brighter, sharper, or out of nothing. This part is about *believing* them. Cheap editing tools, and now generative models that synthesize a convincing photograph from a sentence, have severed the old reflexive link between "photograph" and "something that happened." Two responses run in parallel. **Forensics** works on an image you are handed cold — no cooperation, possibly an adversary on the other side — and looks for the statistical and physical fingerprints that authentic capture leaves and editing or generation disturbs. **Authentication** works the other way around: it asks creators and cameras to *sign* their work and every edit to it, so trust comes from a verifiable record rather than a hunt for tells. Neither is sufficient alone — forensics gives evidence, not proof, and provenance is opt-in — so the honest position is that they are complementary.
▸41.1 Image Forensics⧉
⬜ figure not yet created
the **forensic-trace cheat sheet** — one tampered composite annotated with the cue each method would catch (PRNU residual, CFA grid break, JPEG ghost, wrong shadow) [fig-forensic-traces fig-forensic-traces
fig-telephoto-vs-retrofocus
fig-telephoto-vs-retrofocus · two two-group schematics — telephoto (+ then −, principal plane H′ pushed in front → physical length < f) vs retrofocus/inverted-telephoto (− then +, long back-focal distance to clear the SLR mirror); marks f vs physical length, H′, F′ ✅
fig-correspondence-then-transport
fig-correspondence-then-transport · the L17 spine — one scene displaced (two views / two faces / two frames / one long frame), each resolved by estimating a coordinate map (homography, morph field, flow, track, motion vector, camera path) then transporting pixels by one shared inverse-warp engine; the finding is hard, the moving is plumbing 🟨
⬜ figure not yet created
correlate a suspect image's residual against camera fingerprints to identify the source / localize a paste [fig-prnu-fingerprint] fig-prnu-fingerprint
⬜ figure not yet created
**JPEG ghost** — re-save at a quality and difference: a region with a different compression history pops out [fig-jpeg-ghost] fig-jpeg-ghost
fig-illum-times-reflectance
fig-illum-times-reflectance · light = illumination × reflectance (per-wavelength) ✅
⬜ figure not yet created
a composited face lit from the wrong side [fig-lighting-consistency] fig-lighting-consistency
The premise of all blind forensics: a real photograph is the output of a specific **physical pipeline** — a particular sensor, a color-filter mosaic, a demosaicking algorithm, a lens, a JPEG encoder, a single illumination of a single 3-D scene — and that pipeline stamps the pixels with **consistent low-level regularities**. Splice two photos together, paint something out, scale a pasted region, or synthesize an image from a network, and those regularities are broken locally or never reproduced. Forensics is the art of modeling the expected regularity and flagging where it fails.
▸41.2 Authentication and provenance (C2PA)⧉
fig-learning-transition
fig-learning-transition · book-wide overview: each PART placed on the hand-designed→learned→generative axis with a range bar (foundations classical; single-image/3-D/forensics furthest right); intro 'field in transition' ✅
fig-provenance-vs-forensics
fig-provenance-vs-forensics ·
fig-telephoto-vs-retrofocus
fig-telephoto-vs-retrofocus · two two-group schematics — telephoto (+ then −, principal plane H′ pushed in front → physical length < f) vs retrofocus/inverted-telephoto (− then +, long back-focal distance to clear the SLR mirror); marks f vs physical length, H′, F′ ✅
fig-c2pa-manifest
fig-c2pa-manifest ·
fig-c2pa-chain
fig-c2pa-chain ·
fig-durable-credentials
fig-durable-credentials ·
fig-content-credentials-ui
fig-content-credentials-ui ·
fig-cos4-vignetting
fig-cos4-vignetting · natural vignetting: relative illumination ∝ cos⁴θ falling toward the corner, with an image-corner darkening illustration (companion to `fig-cos4-falloff`, ties θ to image radius + a picture) ✅
Forensics is a losing race in the limit: as generators improve, the pixel-level tells vanish. Authentication changes the game by **not relying on the pixels to confess**. Instead it asks the *honest* parts of the pipeline — the camera, the editing app, the AI tool, the publisher — to **cryptographically sign what they did**, and binds that signed record to the image. A reader then **verifies a signature against a trust list** rather than hunting for artifacts. The catch, which we keep front and center, is that this is **opt-in**: it can prove an image *is* what it claims, but a missing or stripped credential proves nothing — so it complements forensics rather than replacing it.