Francesco Pinto @ Neurips 2024
@FraPintoML
Postdoc #UChicago, ex-#UniversityOfOxford, #Meta,#Google, #FiveAI, #ETHZurich Trustworthy and Privacy-Preserving ML Email: [email protected]
🚀 Introducing 𝐒𝐚𝐟𝐞𝐖𝐚𝐭𝐜𝐡! 🚀 While generative models 👾🎥 like Sora and Veo 2 have shown us some stunning videos recently, they also make it easier to produce harmful content (sexual🔞, violent🙅♂️, deepfakes🧟♂️). 🔥 𝐒𝐚𝐟𝐞𝐖𝐚𝐭𝐜𝐡 is here to help 😎: the first…
I’ll be at #NeurIPS2024 from now to Sunday. DM here or on Whova to have a chat about (multimodal) large language models privacy, memorisation, training strategies using synthetic data, agents, judges, distribution shift robustness, hallucinations and uncertainty estimation.
Concerned your LLMs 🤖 may regurgitate copyrighted contents ©️ and get you sued? 🩸💸 Fix it with model fusion 🫠 Result of a fantastic collaboration with @JavierAbadM @DonhauserKonst @FannyYangETH 🇨🇭🇬🇧
(1/5) LLMs risk memorizing and regurgitating training data, raising copyright concerns. Our new work introduces CP-Fuse, a strategy to fuse LLMs trained on disjoint sets of protected material. The goal? Preventing unintended regurgitation 🧵 Paper: arxiv.org/pdf/2412.06619
AI coding assistants (e.g. @cursor_ai, @codeiumdev , @github Copilot) are transforming software development—but how secure are they? Our new blog post reveals which tools stand up to security best practices, which introduce hidden vulnerabilities, and what you can do to…
Can't wait for our workshop 'Interpretable AI: Past, Present and Future' @NeurIPSConf ! Check out our super interesting program with talks from @NeelNanda5 , @CynthiaRudin , #RichCaruana , @jxzhangjhu and @TongWang! We'll have a panel moderated by the amazing @kamalikac ! Help…
1/n Happy to share our recent work with @rvolpis @puneetdokania Philip Torr and Grégory Rogez 🚀🤖: Placing Objects in Context via Inpainting for Out-of-distribution Segmentation 🖌️🎨 ->🔍🐏🐏🐺🐏🐏 Paper: arxiv.org/pdf/2402.16392… Code: github.com/naver/poc
In the era of long-context LLMs it is not enough to make models “forget” unsafe knowledge. Adversaries can use this long context to “un-unlearn” the malicious behavior 👿
Unlearning, originally for privacy, today is often discussed as a content-regulation tool. If my model doesnt know X, it is safe. We argue that unlearning provides illusion of safety, since adversaries can inject malicious knowledge back into the models. arxiv.org/pdf/2407.00106
🔥 Excited to be co-organizing this #ECCV2024 workshop with an outstanding line-up of speakers! 🗣️ 🔎Submit if you got papers with new benchmarks and analyses inspecting Emergent Visual abilities ✔️ or limitations ❌of Foundation Models! 🤖
🔥 #ECCV2024 Showcase your research on the Analysis and Evaluation of emerging VISUAL abilities and limits of foundation models 🔎🤖👁️ at the EVAL-FoMo workshop 🧠🚀✨ 🔗 sites.google.com/view/eval-fomo… @phillip_isola @sainingxie @chrirupp @OxfordTVG @berkeley_ai @MIT_CSAIL