HiddenLayer

Persistent AI Backdoors in Safe Model Formats (opens in new tab)

Discover ShadowLogic, a novel backdoor technique that manipulates AI computational graphs. Unlike fine-tuning, these backdoors are 100% persistent across model conversions and resistant to downstream training in "safe" formats like ONNX.

Read the original article
Sign in to keep reading the full article.
Sign UpLog In

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help