17 citations · 17 across the 7 of their papers we have counts for
10 papers
Covert Multi-bit LLM Watermarking: An Information Theory and Coding Approach
Sidong Guo, Tyler Kann, Teodora Baluta +1
We study the problem of multi-bit watermarking for non-autoregressive large language models (LLMs). We introduce an information-theoretic model inspired by diffusion language model…
Model Provenance Testing for Large Language Models
Ivica Nikolic, Teodora Baluta, Prateek Saxena
Large language models are increasingly customized through fine-tuning and other adaptations, creating challenges in enforcing licensing terms and managing downstream impacts. Track…
Explaining SAT Solving Using Causal Reasoning
Jiong Yang, Arijit Shaw, Teodora Baluta +2
The past three decades have witnessed notable success in designing efficient SAT solvers, with modern solvers capable of solving industrial benchmarks containing millions of variab…
User-Customizable Transpilation of Scripting Languages
Bo Wang, Aashish Kolluri, Ivica Nikolić +2
A transpiler converts code from one programming language to another. Many practical uses of transpilers require the user to be able to guide or customize the program produced from…
Membership Inference Attacks and Generalization: A Causal Perspective
Teodora Baluta, Shiqi Shen, S. Hitarth +2
Membership inference (MI) attacks highlight a privacy weakness in present stochastic training methods for neural networks. It is not well understood, however, why they arise. Are t…
LPGNet: Link Private Graph Networks for Node Classification
Aashish Kolluri, Teodora Baluta, Bryan Hooi +1
Classification tasks on labeled graph-structured data have many important applications ranging from social recommendation to financial modeling. Deep neural networks are increasing…
SynGuar: Guaranteeing Generalization in Programming by Example
Bo Wang, Teodora Baluta, Aashish Kolluri +1
Programming by Example (PBE) is a program synthesis paradigm in which the synthesizer creates a program that matches a set of given examples. In many applications of such synthesis…
Private Hierarchical Clustering in Federated Networks
Aashish Kolluri, Teodora Baluta, Prateek Saxena
Analyzing structural properties of social networks, such as identifying their clusters or finding their most central nodes, has many applications. However, these applications are n…
Scalable Quantitative Verification For Deep Neural Networks
Teodora Baluta, Zheng Leong Chua, Kuldeep S. Meel +1
Despite the functional success of deep neural networks (DNNs), their trustworthiness remains a crucial open challenge. To address this challenge, both testing and verification tech…
Quantitative Verification of Neural Networks And its Security Applications
Teodora Baluta, Shiqi Shen, Shweta Shinde +2
Neural networks are increasingly employed in safety-critical domains. This has prompted interest in verifying or certifying logically encoded properties of neural networks. Prior w…