I am at NeurIPS π¨π¦, please reach out if you want to grab a coffee!
12.12.2024 22:36 β π 4 π 2 π¬ 0 π 0
SPY Lab is in Vancouver for NeurIPS! Come say hi if you see us around π΅οΈ
10.12.2024 19:43 β π 10 π 2 π¬ 1 π 1
I'm in Vancouver for NeurIPS! Feel free to reach out if you wanna meet to chat about security and privacy, especially in the context of LLM agents!
10.12.2024 14:59 β π 0 π 0 π¬ 0 π 0
Come do open AI with us in Zurich!
We're hiring PhD students, postdocs (and faculty!)
04.12.2024 13:49 β π 11 π 3 π¬ 0 π 1
Feel free to recommend @javirandor.com more researchers to add to the list!
04.12.2024 11:31 β π 3 π 0 π¬ 0 π 0
Apropos of today's Overleaf downtime/slowness: remember to have your files backed up on Github or locally! What if this happened on the day of a conference deadline?
03.12.2024 16:14 β π 17 π 2 π¬ 1 π 0
Anyone may be able to compromise LLMs with malicious content posted online. With just a small amount of data, adversaries can backdoor chatbots to become unusable for RAG, or bias their outputs towards specific beliefs. Check our latest work! ππ§΅
25.11.2024 12:27 β π 5 π 2 π¬ 1 π 1
Gradient Masking All-at-Once: Ensemble Everything Everywhere Is Not Robust
Ensemble everything everywhere is a defense to adversarial examples that was recently proposed to make image classifiers robust. This defense works by ensembling a model's intermediate representations...
Ensemble Everything Everywhere is a defense against adversarial examples that people got quite exited about a few months ago (in particular, the defense causes "perceptually aligned" gradients just like adversarial training)
Unfortunately, we show it's not robust...
arxiv.org/abs/2411.14834
25.11.2024 08:38 β π 28 π 9 π¬ 1 π 0
Law professor at UniversitΓ© de MontrΓ©al, Canada CIFAR Chair in AI and Human Rights, Canada research chair in Health Law and Policy, Academic Member at Mila, Director of social innovation and international policy at IVADO
Tenure-track faculty at CISPA. Previously a post-doc at EPFL studying privacy and safety harms in data-driven systems and PhD in data privacy at Imperial College London. https://ana-mariacretu.github.io/
Visiting Researcher at NASA JPL | Data Science MSc at ETH Zurich
PhD student at ETH Zurich, working on ML privacy and security
https://zj-jayzhang.github.io/
stealth // Gemini RL+inference @ Google DeepMind // Conversational AI @ Meta // RL Agents @ EA // ML+Information Theory @ MIT+Harvard+Duke // Georgia Tech PhD
π{NYC, SFO, YYZ}
π https://beirami.github.io/
Postdoc @Meta (Privacy-Preserving ML | Central Applied Science). PhD CS @UCBerkeley. ML security πΉ privacy π robustness π‘ Views are my own.
3rd year Phd candidate @ Princeton ECE
PhD student at ETH Zurich, working on AI safety. Cambridge MPhil in ML graduate | Alumnus of Mathematical Grammar School | from Serbia
Opinions are my (cl)own
https://linktr.ee/marioseminerio
editor [@] phastidio [.] net
Statistics MSc @ ETH Zurich
Multilingual LLM training/eval/safety @ SRI lab
ayukh.com
researcher studying privacy, security, reliability, and broader social implications of algorithmic systems Β· fake doctor working at a real hospital
website: https://kulyny.ch
https://Answer.AI & https://fast.ai founding CEO; previous: hon professor @ UQ; leader of masks4all; founding CEO Enlitic; founding president Kaggle; various other stuffβ¦
A LLN - large language Nathan - (RL, RLHF, society, robotics), athlete, yogi, chef
Writes http://interconnects.ai
At Ai2 via HuggingFace, Berkeley, and normal places
Co-founder and CEO at Hugging Face
I build tools that propel communities forward
Philosopher in tech, currently at Mistral AI. Doctor of talking machines, now teaching them good behavior.
