Briland Hitaj

Computer Scientist @SRI_Intl
security, privacy, ML, federated learning, GANs, chess, Formula 1

[Briland Hitaj @BrilandHitaj]

Recently, I had the pleasure of discussing about #PassGPT with some of my colleagues at @SRI_Intl In the article attached, you may find more details on the story: https://t.co/jzB4CRUeDC

@javirandor @fperezcruz @SDSCdatascience

[Briland Hitaj @BrilandHitaj]

Looking forward to @ACSAC_Conf Don’t miss our talk on DNN watermarking! #ACSAC2024

[ACSAC @ACSAC_Conf]

The first #ACSAC2024 #PaperPreview today is TATTOOED by Pagnotta et al., a #DNN #watermarking technique that allows for reliable DNN ownership verification, even in extreme adversarial settings: https://t.co/fl6NjPpHFi
#AI #cybersecurity
@SRI_Intl @BrilandHitaj @fperezcruz

[Briland Hitaj @BrilandHitaj]

@MattP1Tommy Is Max sending a warning message to Red Bull?

[Briland Hitaj @BrilandHitaj]

@MattP1Tommy @MattP1Tommy was this the best 2024 F1 race so far???

[Briland Hitaj @BrilandHitaj]

All hail to the King of Monza! 😍

[Formula 1 @F1]

Grande Charles 🇮🇹

#F1 #ItalianGP

[Brendan Dolan-Gavitt @moyix]

Another entry in a long-running series where Nicholas Carlini breaks ML defenses published at top security conferences with as little effort as possible (in this case a one line bugfix in the eval)

[Briland Hitaj @BrilandHitaj]

I am still in shock about this terrible news! I’ve worked with Sophia on so many projects and I was looking forward to many more to come! Sophia was one of the brightest people I have ever met! She will be missed!

Rest in peace!

[Margin Research @Margin_Research]

Statement on the passing of Sophia d’Antoine, CEO and founder of Margin Research @Calaquendi44

[Briland Hitaj @BrilandHitaj]

Exciting works in the horizon! 😍 #ASCEND #IARPA #ReSCIND @SRI_Intl
https://t.co/uP2vXRDPvz

[Andrej Karpathy @karpathy]

New (2h13m 😅) lecture: "Let's build the GPT Tokenizer"

Tokenizers are a completely separate stage of the LLM pipeline: they have their own training set, training algorithm (Byte Pair Encoding), and after training implement two functions: encode() from strings to tokens, and decode() back from tokens to strings. In this lecture we build from scratch the Tokenizer used in the GPT series from OpenAI.

[Briland Hitaj @BrilandHitaj]

The GOAT coming at Ferrari 🔥

[Scuderia Ferrari HP @ScuderiaFerrari]

Team Statement

Scuderia Ferrari is pleased to announce that Lewis Hamilton will be joining the team in 2025, on a multi-year contract.

[Javier Rando @javirandor]

🧵 Can data poisoning and RLHF be combined to unlock a universal jailbreak backdoor in LLMs?

Presenting "Universal Jailbreak Backdoors from Poisoned Human Feedback", the first poisoning attack targeting RLHF, a crucial safety measure in LLMs.

📖 Paper: https://t.co/ytTHYX2rA1

[Briland Hitaj @BrilandHitaj]

Earlier today, @javirandor did a fantastic presentation at #ESORICS2023 of our recent #PassGPT paper!

If you are attenting ESORICS, make sure you meet and have a chat with Javier on #LLMs, #security, and #privacy

Link to the paper: https://t.co/E4PbOgyF6R

[Florian Tramèr @florian_tramer]

When analyzing ML security and privacy you need to study 𝐬𝐲𝐬𝐭𝐞𝐦𝐬, not just models!

Our new paper shows that privacy is way worse when models are deployed in systems that use data cleaners, output filters, etc.

Paper: https://t.co/6whdgWhg9I
Blog: https://t.co/0G0TQwLmPV

[Briland Hitaj @BrilandHitaj]

@MattP1Gallagher 11/10

[Andrej Karpathy @karpathy]

Love is the solution to AI alignment.

[Briland Hitaj @BrilandHitaj]

We had a nice chat with Nate on #MaliciousLife podcast discussing some of the risks with current state of the art models, especially discussing threats that may come from using unvetted pre-trained models from third party repositories!

https://t.co/jQLYBIQ8wO

[Fernando Perez-Cruz @fperezcruz]

The #MaliciousLife podcast https://t.co/DygHzqpIZ9 has highlighted our MaleficNet https://t.co/HpAndBY1Ca on their latest episode on Is Generative AI Dangerous?
We thank Nate Nelson for reaching out to us and having a challenging conversation about this paper. @BrilandHitaj

[Briland Hitaj @BrilandHitaj]

@wtf1official Toto!!!

[Briland Hitaj @BrilandHitaj]

That's a valid point! LLMs paving the way for Software 2.0! ;)

[Andrej Karpathy @karpathy]

"What would someone need a personal computer for?"
->
"What would someone need a personal LLM node for?"

[Javier Rando @javirandor]

PassGPT has been accepted for #ESORICS2023! Looking forward to exciting discussions on how LLMs can enhance security in password-based systems.

[Briland Hitaj @BrilandHitaj]

In-person team meetings are definitely better! @grantolney 😎