Next up at #enigma2021, Sanghyun Hong will be speaking about "A SOUND MIND IN A VULNERABLE BODY: PRACTICAL HARDWARE ATTACKS ON DEEP LEARNING"
(Hint: speaker is on the
* looks at the robustness in an isolated manner
* doesn't look at the whole ecosystem and how the model is used -- ML models are running in real hardware with real software which has real vulns!
e.g. fault injection attacks, side-channel attacks
* co-location of VMs from different users
* weak attackers with less subtle control
The cloud providers try to secure things, e.g. protections against Rowhammer
... BUT this focuses on the average or best case, not the worst cast!
* negligible effect on the average case accuracy
* but flipping one bit can make significant amount of damage for particular queries
How much damage can a single bit flip cause?
Some strong attackers might be able to hit an "achilles" bit (one that's really going to mess with the model), but weaker attackers are going to hit bits more randomly.
The attacker might want to get their hands on fancy DNNs which are considered trade secrets and proprietary to their creators. They're expensive to make! They need good training data! People want to protect them!
Does this work? Apparently so: they tried it out using a cache side-channel attack and got back the architectures of the fancy DNN back.
More from Lea Kissner
More from Science
"NO LONGER BEST IN THE WORLD"
UNEP's new Human Development Index includes a new (separate) index: Planetary pressures-adjusted HDI (PHDI). News in Norway is that its position drops from #1 to #16 because of this, while Ireland rises from #2 to #1.
Why?
https://t.co/aVraIEzRfh
Check out Norway's 'Domestic Material Consumption'. Fossil fuels are no different here to Ireland's. What's different is this huge 'non-metallic minerals' category.
(Note also the jump in 1998, suggesting data problems.)
https://t.co/5QvzONbqmN
In Norway's case, it looks like the apparent consumption equation (production+imports-exports) for non-metal minerals is dominated by production: extraction of material in Norway.
https://t.co/5QvzONbqmN
And here we see that this production of non-metallic minerals is sand, gravel and crushed rock for construction. So it's about Norway's geology.
https://t.co/y6rqWmFVWc
Norway drops 15 places on the PHDI list not because of its CO₂ emissions (fairly high at 41st highest in the world per capita), but because of its geology, because it shifts a lot of rock whenever it builds anything.
UNEP's new Human Development Index includes a new (separate) index: Planetary pressures-adjusted HDI (PHDI). News in Norway is that its position drops from #1 to #16 because of this, while Ireland rises from #2 to #1.
Why?
https://t.co/aVraIEzRfh
Check out Norway's 'Domestic Material Consumption'. Fossil fuels are no different here to Ireland's. What's different is this huge 'non-metallic minerals' category.
(Note also the jump in 1998, suggesting data problems.)
https://t.co/5QvzONbqmN
In Norway's case, it looks like the apparent consumption equation (production+imports-exports) for non-metal minerals is dominated by production: extraction of material in Norway.
https://t.co/5QvzONbqmN
And here we see that this production of non-metallic minerals is sand, gravel and crushed rock for construction. So it's about Norway's geology.
https://t.co/y6rqWmFVWc
Norway drops 15 places on the PHDI list not because of its CO₂ emissions (fairly high at 41st highest in the world per capita), but because of its geology, because it shifts a lot of rock whenever it builds anything.
An interesting thing about carp is that they can go into anoxic hibernation and switch to an anaerobic metabolism based on converting glycogen to ethanol.
The waste ethanol is diffused out the gills
https://t.co/V3D1umHf04
Carp can switch over to an anaerobic metabolism and quietly exhale booze until the situation gets better.
They basically evolved the same metabolic pathway as yeast, independently.
In theory, if you spent a few thousand years breeding carp for it, you could use them to make booze.
They'd be enormous, almost entirely glycogen deposits with a fish added as an afterthought.
The really interesting thing about anaerobic carp, is that they can go 4-5 months without oxygen by relying on liver glycogen.
You, a human, have only about 100 grams of glycogen in your liver, about 400 more grams in your skeletal muscles. Call it 500 grams total.
In humans, glycogen is also burned for energy. This is where the marathon runner's bonk comes from: you only have about 2,000 calories worth, and running a marathon burns those 2,000 calories.
The waste ethanol is diffused out the gills
https://t.co/V3D1umHf04
Carp can switch over to an anaerobic metabolism and quietly exhale booze until the situation gets better.
They basically evolved the same metabolic pathway as yeast, independently.
In theory, if you spent a few thousand years breeding carp for it, you could use them to make booze.
They'd be enormous, almost entirely glycogen deposits with a fish added as an afterthought.
The really interesting thing about anaerobic carp, is that they can go 4-5 months without oxygen by relying on liver glycogen.
You, a human, have only about 100 grams of glycogen in your liver, about 400 more grams in your skeletal muscles. Call it 500 grams total.
In humans, glycogen is also burned for energy. This is where the marathon runner's bonk comes from: you only have about 2,000 calories worth, and running a marathon burns those 2,000 calories.
💥💥 Situation Update, Dec. 7th – DNI John Ratcliffe, the bogus science of PCR testing and China’s GMO super soldiers
✅ I cover the bogus science behind PCR testing, explaining from a lab science point of view why no PCR instrument can “quantify” anything,
[M. Adams]
1. whether it’s a coronavirus viral load or the percentage of a food that’s GMO. In fact, literally all the tests currently conducted with PCR equipment are scientifically invalid when it comes to diagnosing illness or determining infectiousness. The sample acquisition used for
2. PCR tests — nasal swabs — aren’t even standardized! (100% bogus junk science).
After covering PCR tests, today’s update then goes into detail about Director of National Intelligence (DNI) John Ratcliffe, pointing out that he will be issuing a report on foreign interference
3. in U.S. elections on or before Dec. 18th. If this report confirms the existence of foreign interference that was capable of altering the outcome of the election, it gives President Trump full justification to declare the election null and void and dispatch military troops
4. to seize all ballots and hold a new count under military authority.
👉 Podcast notes and sources:
The office of military commissions has cleared its calendar for December:
https://t.co/u4nFRiUj8m
US military STOCKPILED Pfizer’s mRNA vaccineBEFORE it was approved by theFDA
✅ I cover the bogus science behind PCR testing, explaining from a lab science point of view why no PCR instrument can “quantify” anything,
[M. Adams]
1. whether it’s a coronavirus viral load or the percentage of a food that’s GMO. In fact, literally all the tests currently conducted with PCR equipment are scientifically invalid when it comes to diagnosing illness or determining infectiousness. The sample acquisition used for
2. PCR tests — nasal swabs — aren’t even standardized! (100% bogus junk science).
After covering PCR tests, today’s update then goes into detail about Director of National Intelligence (DNI) John Ratcliffe, pointing out that he will be issuing a report on foreign interference
3. in U.S. elections on or before Dec. 18th. If this report confirms the existence of foreign interference that was capable of altering the outcome of the election, it gives President Trump full justification to declare the election null and void and dispatch military troops
4. to seize all ballots and hold a new count under military authority.
👉 Podcast notes and sources:
The office of military commissions has cleared its calendar for December:
https://t.co/u4nFRiUj8m
US military STOCKPILED Pfizer’s mRNA vaccineBEFORE it was approved by theFDA
Hard agree. And if this is useful, let me share something that often gets omitted (not by @kakape).
Variants always emerge, & are not good or bad, but expected. The challenge is figuring out which variants are bad, and that can't be done with sequence alone.
You can't just look at a sequence and say, "Aha! A mutation in spike. This must be more transmissible or can evade antibody neutralization." Sure, we can use computational models to try and predict the functional consequence of a given mutation, but models are often wrong.
The virus acquires mutations randomly every time it replicates. Many mutations don't change the virus at all. Others may change it in a way that have no consequences for human transmission or disease. But you can't tell just looking at sequence alone.
In order to determine the functional impact of a mutation, you need to actually do experiments. You can look at some effects in cell culture, but to address questions relating to transmission or disease, you have to use animal models.
The reason people were concerned initially about B.1.1.7 is because of epidemiological evidence showing that it rapidly became dominant in one area. More rapidly that could be explained unless it had some kind of advantage that allowed it to outcompete other circulating variants.
Variants always emerge, & are not good or bad, but expected. The challenge is figuring out which variants are bad, and that can't be done with sequence alone.
Feels like the next thing we're going to need is a ranking system for how concerning "variants of concern\u201d actually are.
— Kai Kupferschmidt (@kakape) January 15, 2021
A lot of constellations of mutations are concerning, but people are lumping together variants with vastly different levels of evidence that we need to worry.
You can't just look at a sequence and say, "Aha! A mutation in spike. This must be more transmissible or can evade antibody neutralization." Sure, we can use computational models to try and predict the functional consequence of a given mutation, but models are often wrong.
The virus acquires mutations randomly every time it replicates. Many mutations don't change the virus at all. Others may change it in a way that have no consequences for human transmission or disease. But you can't tell just looking at sequence alone.
In order to determine the functional impact of a mutation, you need to actually do experiments. You can look at some effects in cell culture, but to address questions relating to transmission or disease, you have to use animal models.
The reason people were concerned initially about B.1.1.7 is because of epidemiological evidence showing that it rapidly became dominant in one area. More rapidly that could be explained unless it had some kind of advantage that allowed it to outcompete other circulating variants.
