MyNameIs_Hacker
- Karma
- 17
- Created
- September 22, 2023 (2y ago)
- Submissions
- 0
Real family surname is Hacker. Security engineer and architect for way too long. First name same as ESR. Find me on LinkedIn or fromhn@<firstname><lastname>.com
Currently working on ML and LLM security.
I've advocated at work for a similar strategy using prompt injections and jailbreaks in the dataset, and to abort when those documents are matched. So far no traction. I think overall it is a mistake to build any such…
"First it needs to be instructed to lie" would be better language to use for those not intimately familiar with ML and who might anthropomorphize "incentive". I dare not get into a discussion about the word "lie" here.…
The car was returned with the same battery charge level (96%) that it was picked up with. This isn't a matter of "fuel" being either electrons or petroleum, which is something that the article fails to address.
Have you ever sat in front of your favorite DAW version XX and thought, oh wow so many things, what am I going to do? How about Sonic Pi? Or any modern audio toolset. So much possibility, where to start? Creative…
For those who think this is a cop out; it is known that for most people the ability to learn new languages changes around puberty. The ability to learn, recognize and pronounce phonemes changes when kids are very young.…
Sure some of the CSA's panic a bit, but I've never had one not go along especially after explaining my purpose. I've not seen too many compromises, but some of them were not public. Especially with small businesses like…
Conspiracy Theory: The proliferation of honeypots is due to secret government contracts attempting to corrupt the usefulness of Shodan and the like.
You forgot 3) It requires money to fix the problem, and Google has become such a bureaucratic mess, that it can't get out its own way to do it. Those of us in large corporations see that pattern quite often.
What ChatGPT missed here is that when bubbles collapse, the damage can extend beyond its edges. So even some perfectly viable AI use case that doesn't require the bubble's financial largess may suffer damage from the…
It seldom creates significant inconvenience or financial obligations when someone pays additional taxes in your name. It only becomes a significant problem when the fraudster is obtaining money or services in your name.…
That is fine for opening a deposit account. The fraud we're talking about is for obtaining credit or future financial obligations. It is wrong to let this be done with so little proof of identity and enforce the…
Same here. I call them canary email addresses when I have to describe it to someone, so I can tell when that organization loses its data. For those of us crazy enough to do this, I came up with another type of canary, a…
Thanks for the link, I hadn't read that paper yet. One of the reasons not to just use the adversarial attack umbrella is that the defenses are likely to be dependent on specific scenarios. Normalization, sanitization,…
The problem with jailbreaking is that it has a specific definition in other settings already, and that is as a goal, not as a method. Jailbreaking a phone might be just run an app with an embedded exploit, or might…
Prompt injection is a method. Jailbreaking is a goal.
If a young'un should ask my age, I report it in hex. Keeps 'em on their toes.
I have an 1800 watt 12v inverter in the trunk of my Prius and have pre-wired AMP cables to the battery for easy hookup for any family member not as technically inclined. This is limited, but I was able to run the oil…