Publications (25)
Can LLMs Follow Simple Rules?
Norman Mu, Sarah Chen, Zifan Wang +6
BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?
Fengqing Jiang, Yichen Feng, Yuetai Li +3
Vulnerability Detection with Code Language Models: How Far Are We?
Yangruibo Ding, Yanjun Fu, Omniyyah Ibrahim +6
Can LLMs Ask Good Questions?
Yueheng Zhang, Xiaoyuan Liu, Yiyou Sun +5
Preventing Prompt Injection with Type-Directed Privilege Separation
Dennis Jacob, Emad Alghamdi, Zhanhao Hu +2
PromptArmor: Simple yet Effective Prompt Injection Defenses
Tianneng Shi, Kaijie Zhu, Zhun Wang +13
Secret-Key Agreement with Public Discussion subject to an Amplitude Constraint
Marwen Zorgui, Zouheir Rezki, Basel Alomair +1
Global Practical Node and Edge Synchronization in Kuramoto Networks: A Submodular Optimization Framework
Andrew Clark, Basel Alomair, Linda Bushnell +1
Adaptive Mitigation of Multi-Virus Propagation: A Passivity-Based Approach
Phillip Lee, Andrew Clark, Basel Alomair +2
JobBench: Aligning Agent Work With Human Will
Yuetai Li, Yichen Feng, Zhangchen Xu +21
Polyhedral Instability Governs Regret in Online Learning
Yuetai Li, Fengqing Jiang, Yichen Feng +6
Submodularity in Input Node Selection for Networked Systems
Andrew Clark, Basel Alomair, Linda Bushnell +1
The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
Fengqing Jiang, Yuetai Li, Yichen Feng +6
Input Selection for Performance and Controllability of Structured Linear Descriptor Systems
Andrew Clark, Basel Alomair, Linda Bushnell +1
GradShield: Alignment Preserving Finetuning
Zhanhao Hu, Xiao Huang, Patrick Mendoza +4
JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
Julien Piet, Xiao Huang, Dennis Jacob +7
Jatmo: Prompt Injection Defense by Task-Specific Finetuning
Julien Piet, Maha Alrashed, Chawin Sitawarin +5
On the Structure and Computation of Random Walk Times in Finite Graphs
Andrew Clark, Basel Alomair, Linda Bushnell +1
Minimizing Convergence Error in Multi-Agent Systems via Leader Selection: A Supermodular Optimization Approach
Andrew Clark, Basel Alomair, Linda Bushnell +1
Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?
Yichen Feng, Yuetai Li, Chunjiang Liu +14
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
Peizhi Niu, Wenjie Qu, Shangding Gu +14
Defending Against Prompt Injection with DataFilter
Yizhu Wang, Sizhe Chen, Raghad Alkhudair +2
PromptShield: Deployable Detection for Prompt Injection Attacks
Dennis Jacob, Hend Alzahrani, Zhanhao Hu +2
Combinatorial Algorithms for Control of Biological Regulatory Networks
Andrew Clark, Phillip Lee, Basel Alomair +2
SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing
Aidan Wen, Norah A. Alzahrani, Jingzhi Jiang +5