Back to Events

Seminar Series

June 24

Boltz: Towards a Unified Approach for Biomolecular Interaction Modeling

Gabriele Corso and Jeremy Wohlwend

Part Of

7:00P
- 9:00P

Location

32-G449
Add to Calendar 2025-06-24 19:00:00 2025-06-24 21:00:00 America/New_York Boltz: Towards a Unified Approach for Biomolecular Interaction Modeling 7:00 PM, Tuesday, 24 June 2025MIT Room 32-G449 (Kiva) and online via ZoomBoltz: Towards a Unified Approach for Biomolecular Interaction Modeling[With updates on new features in Boltz-2 including the ability to predict Binding Affinity]Gabriele Corso and Jeremy WohlwendPlease register in advance for this seminar even if you plan to attend in person at https://acm-org.zoom.us/webinar/register/3917463193515/WN_U1yhFblMQO-I4n1cBhkBFwAfter registering, you will receive a confirmation email containing information about joining the webinar.Indicate on the registration form if you plan to attend in person.  This will help us determine whether the room is close to reaching capacity. We plan to serve light refreshments (probably pizza) before the talk starting at around 6:30 pm. Letting us know you will come in person will help us determine how much pizza to order.We may make some auxiliary material such as slides and access to the recording available after the seminar to people who have registered.Abstract:Accurately modeling biomolecular interactions is a central challenge in modern biology. While recent advances, such as AlphaFold3 and Boltz-1, have substantially improved our ability to predict biomolecular complex structures, these models still fall short inpredicting binding affinity, a critical property underlying molecular function and therapeutic efficacy. In this talk, we present Boltz-2, a new structural biology foundation model that exhibits strong performance for both structure and affinity prediction. Boltz-2introduces controllability features including experimental method conditioning, distance constraints, and multi-chain template integration for structure prediction, and is, to our knowledge, the first AI model to approach the performance of free-energy perturbation (FEP) methods in estimating small molecule--protein binding affinity.  Crucially, it achieves strong correlation with experimental readouts on many benchmarks, while being at least 1000 times more computationally efficient than FEP.For more information see boltz-2 infoBio:Jeremy Wohlwend and Gabriele Corso received PhDs this spring for work at the MIT Computer Science and Artificial Intelligence Laboratory where their research focuses on developing novel ML frameworks to tackle challenging problems in drug discovery and  immunology. Directions to 32-G449 - MIT Stata Center, 32 Vassar Street, Cambridge, MA: Please use the main entrance to the Stata Center at 32 Vassar Street (the entrance closest to Main street) as those doors will beunlocked. Upon entering, proceed to the elevators which will be on the right after passing a large set of stairs and a MITAC kiosk. Take the elevator to the 4th floor and turn right, following the hall to an open area; 32-G449 will be on the left. Location of Stata on campus map.This joint meeting of the Boston Chapter of the IEEE Computer and EMBS Societies and GBC/ACM will be hybrid (in person and online).Up-to-date information about this and other talks is available online at http://ewh.ieee.org/r1/boston/computer/. You can sign up to receive updated status information about this talk and informational emails about future talks at http://mailman.mit.edu/mailman/listinfo/ieee-cs,our self-administered mailing list. TBD

April 24

March 07

How Privacy Enhancing Technologies (PETs) let governments and business share sensitive data while protecting privacy Simson Garfinkel

Part Of

7:00P
- 8:00P

Location

32-G449
Hybrid: Kiva + Virtual: please register at https://acm-org.zoom.us/webinar/register/6917379974134/WN_jwgTYmklQSu6Thc23XOMtQ
Add to Calendar 2025-03-06 19:00:00 2025-03-06 20:00:00 America/New_York How Privacy Enhancing Technologies (PETs) let governments and business share sensitive data while protecting privacy Simson Garfinkel Boston Chapter of IEEE Computer Society and GBC/ACM7:00 PM, Thursday, 6 March 2025MIT Room 32-G449 (Kiva) and online via Zoom How Privacy Enhancing Technologies (PETs) let governments and business share sensitive data while protecting privacySimson Garfinkel Please register in advance for this seminar even if you plan to attend in person athttps://acm-org.zoom.us/webinar/register/6917379974134/WN_jwgTYmklQSu6Thc23XOMtQ After registering, you will receive a confirmation email containing information about joining the webinar.Indicate on the registration form if you plan to attend in person. This will help us determine whether the room is close to reaching capacity. We plan to serve light refreshments (probably pizza) before the talk starting at around 6:30 pm. Letting us know you will come in person will help us determine how much pizza to order.We may make some auxiliary material such as slides and access to the recording available after the seminar to people who have registered.Abstract:Tax returns and financial filings, health records, education records, and crime data are just some of detailed and highly sensitive data that governments have about people.Businesses also have huge archives of sensitive data, including consumer purchases, cellphone mobility traces, and video surveillance. Today a tiny fraction of these data are released as “open data” or sold as “de-identified data.” The rest are locked up, unable to benefit society or promote new economic activity. Worse, much of that allegedly de-identified data can actually be re-identified, as happened when journalists at The Pillar used de-identified data to identify Catholic priests who were going to gay bars and using hookup apps.Privacy Enhancing Technologies (PETs) use advanced mathematics and computational techniques to let organizations analyze and publish sensitive data while protecting the privacy of individuals and sensitive data from organizations. These techniques have existed for decades and are increasingly being deployed by governments and businesses. PETs are not without controversy. When the US Census Bureau adopted a PET called “differential privacy” for the 2020 Census, more than 4000 academics signed an open letter voicing their opposition: they were concerned that differential privacy would do such a good job protecting privacy that the resulting data would be useless for academic research.This talk presents the case for PETs, explains popular PETs for a non-technical audience, and discusses the specific controversy of deploying differential privacy for the 2020 US Census.This is discussed in more detail in his latest book Differential Privacy .Bio:Simson Garfinkel is the Chief Scientist and Chief Operating Officer of BasisTech in Somerville, Massachusetts. He was previously a program scientist at AI2050, part of Schmidt Futures. He has held several roles across government, including a Senior Data Scientist at the Department of Homeland Security, the US Census Bureau's Senior Computer Scientist for Confidentiality and Data Access and a computer scientist at the National Institute of Standards and Technology. From 2006 to 2015, he was an associate professor at the Naval Postgraduate School in Monterey, California. In addition to his research, Garfinkel is a journalist, an entrepreneur and an inventor; his work is generally concerned with computer security, privacy and information technology.Simson is the author or co-author of 16 books, and the author of more than a thousand articles. He is a contributing writer for Technology Review and has written as a freelancer for many publications including Wired magazine, The Boston Globe, Privacy Journal, and CSO Magazine. His work for CSO Magazine earned him five regional and national journalism awards, including the Jesse H. Neal Business Journalism Awards in 2003 and 2004. He is also the editor of The Forensics Wiki. Directions to 32-G449 - MIT Stata Center, 32 Vassar Street, Cambridge, MA: Please use the main entrance to the Stata Center at 32 Vassar Street (the entrance closest to Main street) as those doors will be unlocked. Upon entering, proceed to the elevators which will be on the right after passing a large set of stairs and a MITAC kiosk. Take the elevator to 4th floor and turn right, following the hall to an open area; 32-G449 will be on the left. Location of Stata on campus map  This joint meeting of the Boston Chapter of the IEEE Computer Society and GBC/ACM will be hybrid (in person and online).Up-to-date information about this and other talks is available online at https://ewh.ieee.org/r1/boston/computer/. You can sign up to receive updated status information about this talk and informational emails about future talks at https://mailman.mit.edu/mailman/listinfo/ieee-cs, our self-administered mailing list. TBD

January 09

AI and Trust

Bruce Schneier
Chief of Security Architecture at Inrupt, Inc.

Part Of

6:00P
- 9:00P

Location

32-449 Kiva
Add to Calendar 2025-01-09 18:00:00 2025-01-09 21:00:00 America/New_York AI and Trust Boston Chapter of IEEE Computer Society and GBC/ACM7:00 PM, Thursday, 9 January 2025MIT Room 32-G449 (Kiva) and online via ZoomAI and TrustBruce SchneierPlease register in advance for this seminar even if you plan to attend in person at https://acm-org.zoom.us/webinar/register/7817341052674/WN_CYgexNC-Ssmbzi0gRF234QAfter registering, you will receive a confirmation email containing information about joining the webinar.Indicate on the registration form if you plan to attend in person. This will help us determine whether the room is close to reaching capacity. We plan to serve light refreshments (probably pizza) before the talk starting at around 6:30 pm. Letting us know you will come in person will help us determine how much pizza to order.We may make some auxiliary material such as slides and access to the recording available after the seminar to people who have registered.Abstract:AI and Trust: Trusting a friend and trusting a service are fundamentally different. The former is personal and intimate, while the latter is impersonal and can scale to all of human society. The companies behind the current generative AI systems are poised to exploit that difference. Their intimate conversational nature will cause us to think of them as friends when they are actually services, and trusted confidents when they will actually be working against us. Like much of the internet, these systems will collect our personal data behind our backs and try to manipulate our behavior. Enabling trust in AI systems will require two things. The first are foundation models that are not controlled by corporations and the profit motive. The second is government regulation of the industry. Democratic governance is how we create social trust in our society.Bio:Bruce Schneier is an internationally renowned security technologist, called a "security guru" by the Economist. He is the New York Times best-selling author of 14 books -- including A Hacker's Mind -- as well as hundreds of articles, essays, and academic papers. His influential newsletter Crypto-Gram and blog Schneier on Security are read by over 250,000 people. Schneier is a Lecturer in Public Policy at the Harvard Kennedy School, a faculty affiliate at the Ash Center for Democratic Governance and Innovation at HKS, a fellow at the Berkman-Klein Center for Internet and Society at Harvard University, a board member of the Electronic Frontier Foundation and AccessNow, and an advisory board member of EPIC and VerifiedVoting.org. He is the Chief of Security Architecture at Inrupt, Inc.This joint meeting of the Boston Chapter of the IEEE Computer Society and GBC/ACM will be hybrid (in person and online), part of getting back to normal after the COVID-19 lockdown.Up-to-date information about this and other talks is available online at https://ewh.ieee.org/r1/boston/computer/. You can sign up to receive updated status information about this talk and informational emails about future talks at https://mailman.mit.edu/mailman/listinfo/ieee-cs, our self-administered mailing list.