ZERO-SHOT BLACK-BOX DETECTION OF NEURAL TROJANS
Example systems, methods, and apparatus are disclosed herein for zero-shot black-box detection of neural Trojans.
1 . A system for zero-shot black-box detection of neural Trojans comprising:
a server;
a processor;
memory storing instructions, which when executed by the processor, cause the processor to apply a zero-shot black-box detection of neural Trojans algorithm.
2 . The system of claim 1 , wherein the zero-shot black-box detection of neural Trojans algorithm is:
1:
X ← random Trigger( )
2:
for k = 1, . . . , s do
3:
T
←
ϵ
·
(
1
?
+
?
-
1
?
+
?
)
?
indicates text missing or illegible when filed
4:
X new ← randomNeighbor(X)
5:
C old ← cASR(X)
6:
C new ← cASR(X new )
7:
Δ C ← C new − C old
8:
if Δ C > 0 then
9:
X ← X new
10:
else
if
e
Δ
C
T
≥
random
(
0
,
1
)
then
11:
X ← X new
12:
end if
13:
end for
3 . A method of using zero-shot black-box detection of neural Trojans comprising:
receiving a patch;
performing simulated annealing on the patch using a zero-shot black-box detection of neural Trojans algorithm;
detecting the presence of a Trojan.
4 . The method of claim 3 , wherein the patch includes at least one of a random pattern, a size, a shape, or a location.
5 . The method of claim 4 , wherein the zero-shot black-box detection of neural Trojans algorithm is:
1:
X ← random Trigger( )
2:
for k = 1, . . . , s do
3:
T
←
ϵ
·
(
1
?
+
?
-
1
?
+
?
)
?
indicates text missing or illegible when filed
4:
X new ← randomNeighbor(X)
5:
C old ← cASR(X)
6:
C new ← cASR(X new )
7:
Δ C ← C new − C old
8:
if Δ C > 0 then
9:
X ← X new
10:
else
if
e
Δ
C
T
≥
random
(
0
,
1
)
then
11:
X ← X new
12:
end if
13:
end for