David Lie retweeted
U of T researchers demonstrate AI worm could target any online device: uofteng.ca/d9947n
ALT U of T Engineering professor Nicolas Papernot sitting on a chair and looking out a window.
David Lie retweeted
We have just extended our deadline to May 7 AOE, welcome to submit your AI for good paper to our ICML workshop on Trustworthy AI for Good ☀️! Non-archival allowed. trustworthy-ai-for-good.gith…
10 days left to submit to the 1st Trustworthy AI for Good (AI4GOOD) workshop at #ICML2026! @icmlconf
We're giving out multiple awards and travel funds sponsored by @schmidtsciences and @coop_ai:
🏆 Best Paper Awards (including targeted prizes for cooperative AI theme)
🏆 Top Reviewer Awards
✈️ Travel Funds
Submit here → openreview.net/group?id=ICML…
⏰ Deadline: May 3, 2026 (AoE) 📌 Notification: May 18, 2026 🔗(We extended our deadline to accommodate more submissions!)
Join us in Seoul for discussions bridging AI safety, social good, and governance with keynote speakers @Yoshua_Bengio, @OanaIgnatRo, @jzl86, @maksym_andr, and more!
David Lie retweeted
AI is threatening our democratic society—by concentrating power, narrowing how we think, and flooding institutions faster than they can keep up. These risks emerge at the system level, and technical work alone won't fix them.
👉Check out our whitepaper with 25+ researchers: zhijing-jin.com/d/2026-ai-ri…
💡We introduce 7 threat models and ways forward.
✍️Led by @davidguzman1120 with @DaveRBanerjee, @blin_kevin, @PepijnCobben, @gcorsi_, @x_angelohuang, @ChanglingXavier, Suvajit Majumder, @psyonp, @SimkoSamuel, @strauss_irene, and @TerryJCZhang
Advised by senior co-authors: @ashton1anderson, @Yoshua_Bengio, @MatthiasBethge, @RogerGrosse, Karoline Helbig, @david_lie, Richard Mallah, @radamihalcea, Susan Nesbitt, Susan Perry, @presnick, Stuart Russell, @mrinmayasachan, @bschoelkopf @audreyt and @ZhijingJin
Thank you to all the institutional support from @JinesisLab @EuroSafeAI @MPI_IS @CIFAR_News @iapsAI @CARMA_411 @Cambridge_Uni @UofTCompSci @VectorInst @TorontoSRI @Mila_Quebec @LawZero_ @uni_tue @michigan_AI @UMichCSE @AUParis @UNESCO @UCBerkeley @ETH_en @ETH_AI_Center @ELLISInst_Tue @ELLISforEurope @EthicsInAI #CivicAI
#AISafety #AIGovernance #Democracy #ResponsibleAI
Claude’s Mythos isn’t just an issue about capability. It’s also about control.
In @globeandmail , @schneierblog & I examine @AnthropicAI new model, which is capable of discovering & exploiting software vulnerabilities at unprecedented scale. 📰tinyurl.com/3b6j8u38 (paywall)
New vulnerability in AMD confidential computing systems we discovered revealed at Usenix Security 2025!
Read more here:
security.csl.toronto.edu/blo…
Had an inspiring time at the United Nations Workshop on Responsible AI for Peace & Security! security.csl.toronto.edu/blo…
Congratulations to Shawn and John, 2 newly minted PhD students! security.csl.toronto.edu/blo…
2 TossLab papers at NDSS 2025 next week! security.csl.toronto.edu/blo…
The Citizen Lab at the University of Toronto has a faculty opening! If you work in the areas of internet technologies, human rights and global security, please consider applying! jobs.utoronto.ca/job/Toronto…
I'm excited to be a member of the SIGSAC PROTECT committee (sigsac.org/protect.html)! Peer-review integrity is among the most important pillars of our scientific discpline and I'm honoured that as PC Chair for CCS 2025, I can be part of this crucial initiative to protect it.!
Shirley's Paper on using ML to accelerate symbolic execution will appear at SANER 2024! security.csl.toronto.edu/blo…
We're looking for nominations for PC members for CCS 2024. If you have someone to nominate or would like to self-nominate, head over to this link: forms.gle/dFH3ykrBNEHFNRZy9
Two upcoming papers at ASE 2023 and RAID 2023!
I’m excited to share that Eric's paper on LLVM compiler fuzzing and John's paper on selectively using variable pointer repesentations for memory safety have been accepted at upcoming conferences!
security.csl.toronto.edu/blo…
Watch Shawn's DSN 2023 talk, given at the Hall Árabe in the historic Palacio de Bolsa:
security.csl.toronto.edu/blo…
Wendy's Paper on Classifying Privacy Policies using Calpric Accepted at Usenix Security!
See security.csl.toronto.edu/blo…
This award would not be possible without the help of all my students and wonderful collaborators (both here at U of T and across the world) I've had through my years as a faculty member. Thanks to you all for making this happen! security.csl.toronto.edu/blo…
David Lie retweeted
💡 New on our site: What is the future of cybersecurity regulation in Canada and beyond? A recent roundtable hosted by SRI Research Lead @david_lie explored what trends and solutions are on the horizon.
Learn more: uoft.me/92S
ALT A colourful model of a globe overlaid with a white grid. Image generated in Midjourney.
$1.5M funding awarded to our team from the DND-IDEaS program security.csl.toronto.edu/blo…