Cool news article by Ed Targett covering our recent paper! “Mantis Framework" poisons, traps hackers' AI agents in a tarpit thestack.technology/mantis-framewo…

LLMmap: Fingerprinting For Large Language Models "With as few as 8 interactions, LLMmap can accurately identify 42 different LLM versions with over 95% accuracy. More importantly, LLMmap is designed to be robust across different application layers, allowing it to identify LLM

Prompt Injection Defenses Against LLM Cyberattacks schneier.com/blog/archives/…

#GeorgeMasonResearch Evgenios Kornaropoulos of Mason CEC comments in this story: AI About-Face: 'Mantis' Turns LLM Attackers Into Prey darkreading.com/cybersecurity-…

🚨Exciting Faculty Positions Penn Engineering! Join our AI for Science initiative backed by $750M investment & shape the future of scientific discovery through AI/ML, from materials design and drug discovery to autonomy and climate modeling. ✨Here's what we offer:

Computer Science at CCNY is hiring. It's quite an exciting time to be working in Computational Sciences at CUNY with the recent DoE funded TREAD Center and the Simons Foundation investment in our University. cuny.jobs/new-york-ny/as…

Our team at Google DeepMind Gemini Live is hiring multiple summer Research Interns! Our research interest spans various aspects of multimodal LLM agents including multimodality, factuality, reasoning... If you are interested, please apply here: forms.gle/MVEJokvfNx5b9t…

.Mason CEC professor receives an NSF CAREER Award for his work on privacy and data security. Discover more⬇️ #MasonNation gmu.edu/news/2025-01/u…

Congratulations to Evgenios Kornaropoulos, who received a National Science Foundation (NSF) CAREER award for $648,811 for work on privacy and data security under the title “Encrypted Systems with Fine-Grained Leakage.” cec.gmu.edu/news/2025-01/u…

Brown CS Alum Evgenios Kornaropoulos Receives An NSF CAREER Award To Explore Cryptographic Leakage Evgenios is currently an assistant professor at the George Mason Computer Science Department and completed his graduate studies at Brown. Brown CS News: bit.ly/4iaorqn

I have an opening for a post doc position in machine learning theory, with a deadline of June 1st. Please share and apply: international.au.dk/about/profile/…

IEEE S&P 2027 will take place in Montreal, Canada 🤯

If you are submitting to IEEE S&P this year, a friendly reminder that there is an abstract submission deadline this Thursday May 29 (AoE). More details: sp2026.ieee-security.org/cfpapers.html

Our new paper (led by Dario Pasquini) was featured in the Register! We show that attackers can poison telemetry data to manipulate the AI agent that automates IT operations. Check it out: arxiv.org/pdf/2508.06394

When AIOps Become “AI Oops” - arxiv.org/pdf/2508.06394 AI for IT Operations (AIOps) is transforming how organizations manage complex software systems by automating anomaly detection, incident diagnosis, and remediation. Modern AIOps solutions increasingly rely on autonomous

Pushing the Limits of Frequency Analysis in Leakage Abuse Attacks. arxiv.org/abs/2508.11563

Subverting AIOps Systems Through Poisoned Input Data schneier.com/blog/archives/…