🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

The first cycle deadline has just passed. We wish all the authors good luck with their submissions!

The deadline for the call for workshop CCS 2024 is coming soon. We are humbled and honored to welcome the submission of your workshop proposal! sigsac.org/ccs/CCS2024/ca…

🚀 Registrations are now open for SiMLA workshop co-located with ACNS simla-workshop.github.io/Simla2024/ The keynote will be delivered from Prom Yang Zhang Yang Zhang (CISPA). ACNS @CISPA Ezekiel Soremekun Sudipta @YAMIZIS Thibault Simonetto Jianying Zhou

The call for sponsorship of #CCS2024 is up. sigsac.org/ccs/CCS2024/ca… We are looking forward to receiving contributors from academia, industry, and government to help us share leading-edge ideas on computer and communications security.

Excited to share TrustAIRLab! 🚀 We're dedicated to fostering Trustworthy AI with a focus on safety, privacy, and security. Dive into our libraries for easier algorithm reproduction, benchmarks for ML model attacks & defenses, and more. Check it out ➡️ github.com/TrustAIRLab

Happy to announce that our paper titled "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models got accepted to CCS 2024! Kudos to Xinyue (Vera) Shen for taking the lead on this work! #ccs2024

🚀Just updated: We present our longitudinal robustness tests on LLaMA (v1, v2, v2 Chat, v3, and v3 Instruct), GPT-3.5 (v0613, v1106, and v0125), and GPT-4 (v0613, v1106, v0125, and v0409) across three critical categories: misclassification, jailbreak, and hallucination!

Tomorrow at #ieeesp2024 we will present Mohammad Naseri's paper "BadVFL: Backdoor Attacks in Vertical Federated Learning", in session 6B. Open access: arxiv.org/pdf/2304.08847

Talking to GPT-4o is great, but what if it turned evil? 🚨📷 Our latest research explores Voice Jailbreak Attacks against GPT-4o with an average attack success rate of 77.8%! Check out our paper (arxiv.org/abs/2405.19103) and watch the demo in action!📷#GPT4o #Jailbreak #ChatGPT

Today, we are publishing a new pre-print led by Georgi Ganev. We (attempt to) replicate and audit six open-source implementations of the popular PATE-GAN algorithm, a differentially private generative model used to generate synthetic data. Paper: arxiv.org/abs/2406.13985

If the paper is about trustworthy ML, one venue should be screaming at you ----> SaTML Conference Seriously, I have heard from several folks that they had amazing interactions at SaTML Conference You can actually go around and chat with folks and have in depth conversations about their

happy to share that my former student Zheng Li has won ERCIM WG STM Best Ph.D. Thesis Award 2024! Zheng has published several interesting papers in the field of ML privacy during his phd, I’m looking forward to more cool works from him in the future!

CCS 2024 will happen next week! Are you ready?

I’m recruiting PhD students interested in trustworthy ML and ML for security this cycle! Please reach out via email anytime or find me at ACM CCS 2025 next week. Retweets are greatly appreciated!

We have just published our call for faculty @CISPA (see jobs.cispa.saarland/jobs/detail/255 for S&P and jobs.cispa.saarland/jobs/detail/254 for AI/ML). Application deadline is December 2, AoE. Please spread the news and if you have questions, reach out, I'll be at ACM CCS 2024 next week to chat!

I’m recruiting PhD students interested in system security/privacy, trustworthy ML, UCLA ECE/CS for Fall 2025! Please reach out via email anytime or find me at ACM CCS 2025 next week. Retweets are greatly appreciated!

Are you heading to CCS and want to join @CISPA's networking event there? Great, then show off your knowledge about CISPA and solve our quiz (career.cispa.de/quiz) until Wednesday 5pm (SLC time) and secure your invitation.

CSAW’24 Europe : We are pleased to announce the 10 finalists of the Applied Research Competition, which rewards the best articles published during the year by PhD students in top-ranked papers/conferences. We look forward to seeing you at @Esisar on November 8 for the final!

I am recruiting 1-2 PhD students for Fall 2025 at Princeton to work on Comp Social Science/Societal Impact of GenAI/GenAI for SocSci I wrote a bit about my research flavor & interests here: manoelhortaribeiro.github.io/advising Deadline: December 15th (cs.princeton.edu/grad#prospecti…) Please boost!