News & EventsDepartment Events & Announcements
Events
-
Mar4
EVENT DETAILS
less
The increasing scale and complexity of modern software have led to a surge in security vulnerabilities, outpacing the ability of developers to provide timely repairs. While Large Language Models (LLMs) have catalyzed advancements in Automated Vulnerability Repair (AVR), existing approaches often struggle in real-world settings due to an over-reliance on idealized assumptions, such as perfect fault localization and patch validation methodologies. This dissertation addresses these gaps by developing autonomous, LLM-based systems designed to navigate the end-to-end complexities of the repair process, including 0-day vulnerability mitigation, legacy system maintenance, and rigorous correctness evaluation.
To improve the practicality of AVR, we first introduce PatchAgent, an autonomous agent that integrates fault localization, patch generation, and patch validation. By utilizing a language server and interaction optimization, it mimics human-like reasoning to repair vulnerabilities triggered by proof-of-concept (PoC) inputs, achieving a 90% success rate on real-world datasets. Extending these capabilities to 1-day vulnerabilities, we present PortGPT, a system designed to automate patch backporting for large-scale projects like the Linux kernel. By autonomously navigating Git history and refining patches based on compiler feedback, PortGPT demonstrates high efficacy in migrating security fixes to older software branches, with several generated patches successfully merged into the Linux mainline.
Finally, to address the lack of reliable evaluation standards in the field, we present PVBench, a benchmark designed for the rigorous assessment of patch correctness. Our analysis reveals that existing AVR systems frequently produce "overfitted" patches that pass basic tests but fail to capture the original developer's intent or the true root cause of the vulnerability. By introducing PoC+ tests that encode complex semantic requirements, we demonstrate that current success rates are often significantly overestimated. Collectively, this work provides a comprehensive framework for building and evaluating AVR systems that are robust, autonomous, and applicable to the demands of real-world software maintenance.
TIME Wednesday, March 4, 2026 at 10:30 AM - 1:00 PM
CONTACT Jensen Smith jensen.smith@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Mar10
EVENT DETAILS
lessObserved consolidation in Internet infrastructure is ambiguous: the same concentration level can reflect unavoidable ecosystem constraints or deliberate deployment choices, and these regimes produce measurably different consequences. This dissertation introduces a comparative framework that distinguishes structural consolidation from strategic consolidation by interpreting government web infrastructure relative to the surrounding commercial ecosystem in each country. Across 61 countries and over a million URLs, it measures provider concentration in content hosting, authoritative DNS, and certificate authorities, and shows that similar concentration levels arise for fundamentally different reasons.
The framework enables a second contribution: interpreting what consolidation means for users. The dissertation shows that practical redundancy is limited regardless of consolidation type. Strategic centralization does not buy better fallback than structurally constrained ecosystems provide. It shows that structural consolidation produces uniform foreign exposure while strategic consolidation produces high variance, and that path-level dependencies introduce jurisdictional exposure that hosting level analysis alone cannot detect. It shows that consolidation shapes performance both through infrastructure placement and through opaque content delivery steering, and introduces a methodology to infer CDN replica selection strategies at a global scale.
Taken together, this work argues that concentration metrics alone underspecify the phenomenon they claim to measure. By providing a comparative baseline that separates how concentrated from why concentrated, it offers a foundation for more rigorous interpretation of Internet consolidation across sectors and countries.
TIME Tuesday, March 10, 2026 at 10:00 AM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Jensen Smith jensen.smith@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Mar11
EVENT DETAILS
lessWednesday / CS Seminar
March 11 / 12:00 PM
Hybrid / Mudd 3514Speaker
Li "Harry" Zhang, Drexel UniversityTalk Title
Auto-Formalization for Trustworthy PlanningAbstract
Despite the rapid advancement of AI, most systems in high-stakes applications remain primarily limited to rule-based interactions and cannot reliably plan or execute complex user tasks. Despite recent efforts in using large language models (LLMs) to plan as agents, their hallucinations and lack of verifiability undermine executability and trust, preventing real-world deployment. This proposal advances an alternative paradigm: LLM-as-formalizer. Instead of relying on LLMs to generate plans directly, we use them as a code generator to translate a user’s environment and goal into formal languages (such as PDDL) that can be deterministically solved by off-the-shelf solvers. This neurosymbolic approach combines the flexibility of LLMs with the reliability of symbolic systems, offering a pathway toward trustworthy, generalizable planning. In this talk, I will discuss a few advances in 2025 including a comprehensive evaluation of LLM's auto-formalization ability under a unified methodological framework, and also ongoing work on iterative and multi-agent planning in partially observable environments.Biography
Li "Harry" Zhang is an assistant professor at Drexel University, focusing on Natural Language Processing (NLP) and artificial intelligence (AI). He obtained his PhD degree from the University of Pennsylvania in 2024, advised by Prof. Chris Callison-Burch and chaired by Prof. Dan Roth. He was a year-long intern in 2023 at the Allen Institute for Artificial Intelligence. He obtained his Bachelor's degree from the University of Michigan in 2018, mentored by Prof. Rada Mihalcea and Prof. Dragomir Radev. His research agenda use large language models (LLMs) as auto-formalizers for trustworthy problem-solving, accepted to the AAAI 2026 New Faculty Highlights program. He has published more than 30 peer-reviewed papers in NLP and AI conferences, such as ACL, EMNLP, and NAACL, that have been cited more than 3,000 times. He also consistently serves as Area Chair, Session Chair, and reviewer in those venues. Outside academia, he is a sponsored musician, producer, and content creator having over 60,000 subscribers across streaming platforms.Research Interests: NLP, planning, reasoning, code generation
TIME Wednesday, March 11, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Mar11
EVENT DETAILS
lessSpeaker: Zeyu Liu, Yale University
Title: Recent Advancements in Single-Server Oblivious Message Retrieval
Abstract: Anonymous message delivery systems, such as private messaging services and privacy-preserving blockchains, require mechanisms that allow recipients to retrieve messages addressed to them without leaking metadata or enabling message linkage. A simple approach is for recipients to download all posted messages and locally scan for those addressed to them, but this becomes prohibitively expensive in terms of communication and computation at scale.
We show how untrusted servers can detect messages on behalf of recipients and aggregate them into a compact encrypted digest that recipients can efficiently decrypt, via the cryptographic primitive Oblivious Message Retrieval. These servers operate obliviously and learn nothing about which messages are addressed to which recipients. Privacy, soundness, and completeness are guaranteed even if all parties except the recipient are adversarial and colluding. Moreover, our model and constructions generalize naturally to group messaging or mailing lists, where senders can generate messages that are efficiently detectable by multiple designated recipients.
In this talk, we begin with an asymptotically efficient construction based on Fully Homomorphic Encryption and homomorphically encoded Sparse Random Linear Codes. We then discuss recent advancements that lead to concretely efficient instantiations of this paradigm. Finally, we address additional security considerations, including resilience to denial-of-service attacks.
Bio: Zeyu Liu is a PhD student at Yale University, advised by Ben Fisch. He received his MS from Columbia University, where he was advised by Tal Malkin and Eran Tromer. His research focuses on cryptography, including fully homomorphic encryption, metadata privacy, and lattice-based cryptography.
TIME Wednesday, March 11, 2026 at 12:00 PM - 1:00 PM
LOCATION 3001, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Xiao Wang wangxiao@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Mar12
EVENT DETAILS
lessHosted By CSPAC
Speaker: David KrasowskaTitle: Architecting Task-Based Execution Across GPU Clusters and PIM Architectures
Abstract: Writing parallel and distributed programs is notoriously difficult. This talk explores how task-based programming frameworks can reduce this burden across increasingly heterogeneous and distributed hardware. First, I present cuNumeric.jl and Legate.jl, which transparently scale idiomatic Julia array workloads across CPUs and GPUs. Second, I shift focus to extending task-based programming models to emerging Processing-in-Memory (PIM) architectures. I introduce libvectordpu, a high-performance tasking model for direct DPU programming, and Legion-PIM, which integrates DPUs into the core Legion programming system. Ultimately, moving computation near memory requires more than just a new backend– it fundamentally reshapes our assumptions about task granularity, data partitioning, and locality.
---
What is CSPAC?
We are the CS PhD Advisory Council. We are a PhD student-led organization, and our mandate is to interface between PhD students and faculty on academic issues. We want to advocate for PhD students in the department, so if there is some way we can support you, please come talk to us. We welcome PhD students to our weekly meetings on Tuesdays, 4:00-5:00pm in Mudd 3501 and on zoom. We also welcome anonymous concerns/feedback at any time via this form. Anyone in the community can reach us at cspac@u.northwestern.edu.TIME Thursday, March 12, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT CSPAC cspac@u.northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Apr6
EVENT DETAILS
lessMonday / CS Joint Seminar
April 6 / 3:00 PM
Ford Motor ITWA joint seminar presented by Mechanical Engineering, Computer Science, and the Center for Human–Computer Interaction + Design
Speaker
Faez Ahmed, Massachusetts Institute of TechnologyTalk Title
From Data to Design: Rethinking Engineering Design With Next-Gen AIAbstract
Generative AI is transforming how we create, customize, and accelerate digital content. Yet applying these tools to engineering design introduces unique challenges, from maintaining precision under evolving requirements to working effectively in data-scarce environments and interpreting designer intent. In this talk, I will discuss these challenges and show how emerging engineering-focused foundation models are beginning to address them, reshaping workflows in areas such as vehicle design, CAD automation, and design optimization. I will highlight new opportunities enabled by generative AI that integrates multimodal data with engineering analysis and optimization, and present examples of AI-driven design co-pilots for engineering tasks. The talk will conclude with a perspective on how AI enables us to broaden design democratization, accelerate innovation cycles, and fundamentally reshape the role of engineers.Biography
Faez Ahmed is an Associate Professor of Mechanical Engineering at MIT, where heleads the DeCoDE Lab. His research focuses on AI for engineering design, including deep generative models, multimodal representations, and human–AI collaboration. His work has been recognized with the NSF CAREER Award, ASME DAC and DTM Young Investigator Awards, the Google Research Scholar Award, and the Amazon Research Award. He serves as an Associate Editor for Computer-Aided Design and Design Science.TIME Monday, April 6, 2026 at 3:00 PM - 4:00 PM
LOCATION ITW 1350, Ford Motor Company Engineering Design Center map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Apr13
EVENT DETAILS
lessMonday / CS Seminar
April 13 / 12:00 PM
Hybrid / Mudd 3514Speaker
Arindam BanerjeeTalk Title
TBAAbstract
TBABiography
TBA---
Zoom: TBA
Panopto: TBATIME Monday, April 13, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Apr22
EVENT DETAILS
lessWednesday / CS Seminar
April 22 / 12:00 PM
Hybrid / Mudd 3514Speaker
Lev ReyzinTalk Title
TBAAbstract
TBABiography
TBA---
Zoom: TBA
Panopto: TBATIME Wednesday, April 22, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Apr27
EVENT DETAILS
lessMonday / CS Seminar
April 27 / 12:00 PM
Hybrid / Mudd 3514Speaker
Tushar ChandraTalk Title
TBAAbstract
TBABiography
TBA---
Zoom: TBA
Panopto: TBATIME Monday, April 27, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
Apr29
EVENT DETAILS
lessWednesday / CS Seminar
April 29 / 12:00 PM
Hybrid / Mudd 3514Speaker
Bill FeffermanTalk Title
TBAAbstract
TBABiography
TBA---
Zoom: TBA
Panopto: TBATIME Wednesday, April 29, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)
-
May4
EVENT DETAILS
lessMonday / CS Seminar
May 4 / 12:00 PM
Hybrid / Mudd 3514Speaker
Moon DuchinTalk Title
TBAAbstract
TBABiography
TBA---
Zoom: TBA
Panopto: TBATIME Monday, May 4, 2026 at 12:00 PM - 1:00 PM
LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library) map it
CONTACT Wynante R Charles wynante.charles@northwestern.edu EMAIL
CALENDAR Department of Computer Science (CS)