Adelin Travers

Security & Machine Learning , Views my own.

[Adelin Travers @alkae_t]

My analysis of Apple’s PCC announcement from an AI/ML security perspective

[Trail of Bits @trailofbits]

Apple’s PCC is a game-changer for AI/ML security, but it’s not without flaws. Read our detailed breakdown. https://t.co/2OlmzvDr4S

[Hexacon @hexacon_fr]

The Palais Brongniart is wearing its Hexacon dress to welcome you tomorrow! 💃

[Varun Chandrasekaran @VarunChandrase3]

Some of the most brilliant minds I know are building one benchmark after another instead of finding more principled ways of understanding behaviours. Is this what science has come to?

[Adelin Travers @alkae_t]

@rharang True true

[Adelin Travers @alkae_t]

Totally agree. Application design is primordial in LLM/agentic security because of how hard it is to actually make the model itself safe.

By the way, isn’t that documented as “the golden rule” in the Nvidia Guardrails’ documentation’s LLM security guidelines @rharang ?

[Adelin Travers @alkae_t]

One of the best examples of unintentional data poisoning: replicating a common pattern of public code that was used as training data for an LLM.
Workarounds are everywhere because they are often fast solutions. Actual fixes can often take longer and thus may be less frequent

[Konner @WanderSamsara]

@Sauers_ I had Claude say “here is the error. Let me introduce a workaround until the error is fixed.”

How bout you just fix the error you identified

[Rob Fuller @mubix]

Wanted to share that I just finished my MBA. Two graduate degrees, my undergrad and a CISSP. Now all I have to do is start attending RSA… ;)

[Adelin Travers @alkae_t]

Congrats @VarunChandrase3 and well deserved as always !

[Varun Chandrasekaran @VarunChandrase3]

Thanks @GoogleResearch for your generous gift in supporting our research on trustworthy AI. https://t.co/Y6OrOWEnXk

[Brendan Dolan-Gavitt @moyix]

Okay. Homoglyph jokes are too subtle for this audience. I understand, it’s fine

[Varun Chandrasekaran @VarunChandrase3]

DM is ok, but Chris is fun to work with :D

[moo @moo_hax]

A lot of what I did in the early days of AIRT was actually just building in Security process…

[Yarden Shafir @yarden_shafir]

Does anyone know companies hiring for entry level roles (in Canada/remote)? And I mean *real* entry level, not degree + 2 certs + 3 years experience “entry level”.

Not just cybersecurity, any entry level roles at all, in any area.

[threlfall @WHITEHACKSEC]

Dropbox is looking for a senior ML engineer to join our threat intelligence and product trust & safety team, link in reply. DM me if you want to know more

[Adelin Travers @alkae_t]

Congrats @NicolasPapernot !

[Ilia Shumailov🦔 @iliaishacked]

Attacks such as this highlight the importance of system-level security analysis at all
stages of model deployment, starting as the design of the architecture, and extending towards as late
as the actual deployment of the model and how different user queries are batched together.

[Adelin Travers @alkae_t]

Incredible opportunity right there!

[Ilia Shumailov🦔 @iliaishacked]

Folks, our ML Security & Privacy team at DeepMind is looking for a Student Researcher to start in March in London! What will the student do? Hack and fix LLMs.

Please reach out to me if you have any questions or find me at neurips.

[Florian Roth ⚡️ @cyb3rops]

I strongly recommend turning this off.

It's unbelievable that they quietly enabled this while everyone was focused on their 'Recall' AI feature. Now they're collecting and using everyone's Microsoft Word and Excel data to train their AI models.

[Eleonora Svanberg @EleonoraSberg]

I'm a PhD student at @UniofOxford and I think I'm living in a fairytale :-)

Foxes playing around in the snow at Magdalen College this morning — absolutely magical!