Evgenios Kornaropoulos

STOC 2025 (June 23-27, Prague) Theory Fest is looking for workshop proposals! Deadline March 9, so please hurry and submit your great proposals and please repost!

Link: stoc2025theoryfest.netlify.app

Thank you very much Shravan!

I am extremely excited and honored to receive the NSF CAREER award!

USENIX Security '25 Enigma Track Call for Participation Submissions due: Wednesday, March 5, 2025 Notification to submitters: Wednesday, May 7, 2025

Enigma will be back as a track at USENIX Security: https://www.usenix.org/conference/usenixsecurity25/enigma-cfp

A slide titled "auditing differentially private algorithms"

Another thought-provoking* talk by @thejonullman.bsky.social at the #EnCOREPrivacy25 workshop, on auditing differentially private algorithms by designing membership inference attacks(and why we should, and how).
encoredp.github.io

*The thoughts! They were provoked!

Hello aspiring cybersecurity professors! ASU is hiring faculty in all security disciplines and all levels, and the first deadline is TONIGHT! Apply at apply.interfolio.com... and don't worry --- you can still apply tomorrow if tonight is impossible :-)

Looking for a place to pursue a PhD in theoretical computer science? Consider applying to one of the open positions in the Copenhagen area! We have a large and diverse community within TCS, including the BARC center (barc.ku.dk) and its affiliated research projects in...

Strangely, the above discussion fits well the writing grants objective function.

Here is a list of amazing (applied) crypto folks I found here:

bsky.app/profile/did:...

Anthropic has hired an 'AI welfare' researcher Kyle Fish joined the company last month to explore whether we might have moral obligations to AI systems

AI welfare is a thing: www.transformernews.ai/p/anthropic-...

This is one of the best talks I've seen recently! It highlights how skill sets translate across disciplines and how attacking a problem as an outsider may yield unexpected results. If you are excited about a new area, you should get outside your comfort zone and contribute in your own unique way

Patriot papers aplenty at prestigious ACM CCS conference George Mason University computer science faculty and students are demonstrating once again why the program is so highly ranked, with an impressive showing at an upcoming top-tier academic conference.

#GeorgeMasonResearch George Mason faculty and students presented 10 papers at this year's flagship ACM Computer Security Conference on Computer and Communications Security (CCS) 2024.

Two of these papers won a Distinguished Paper Award!

Theoretical CS Job Market 2024

It's tough to gain visibility as a young researcher, and it's job market season! Are you a theoretical computer science PhD/postdoc on the job market?

I don't have a crazy juge audience but I'll try to help a bit: fill this form, and I'll tweet your pitch and info!
docs.google.com/forms/d/e/1F...

#security #privacy #AI #LLM

This is the first evidence that a challenging attack on AI, i.e., prompt injections, which the community cannot eliminate (as of now), can be turned into something constructive and positive for the security community

(2) once the LLM-agent falls for the trap, then we deploy a prompt injection that can either eat up the resources of the attacking LLM (by luring it to keep looking in an infinite filesystem) or even persuade the LLM-agent to run a reverse shell so the defender can take over the attacker's machine!

This year, we saw the first automated cyberattacks in the wild where LLMs dictated the strategy. We built a proactive defense system to mitigate this threat. Our idea was to (1) exploit the greedy nature of LLMs and lure them to a decoy service that looked vulnerable but unrelated to the real system

AI About-Face: 'Mantis' Turns LLM Attackers Into Prey Experimental counter-offensive system responds to malicious AI probes with their own surreptitious prompt-injection commands.

We had a great discussion with @robertlemos.bsky.social from Dark Reading about our new paper "Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks"(arxiv.org/abs/2410.20911). Mantis turns the hardness of dealing with prompt injections into an opportunity!

This year at IEEE S&P we tried a shorter talk but with a mandatory poster slot immediately after the session (in face in the same room). Worked surprising well! Talk is seen as a teaser for a more elaborate discussion during the poster. Also posters were not crowded cause it was per session.

I am here cause I am hedging my bets. Let's hope that this is the one that will replace the you-know-who