116 citations · 201 across the 10 of their papers we have counts for
6 papers · 1 filter
Does Prompt-Tuning Language Model Ensure Privacy?
Shangyu Xie, Wei Dai, Esha Ghosh +3
Prompt-tuning has received attention as an efficient tuning method in the language domain, i.e., tuning a prompt that is a few tokens long, while keeping the large language model f…
TrojanPuzzle: Covertly Poisoning Code-Suggestion Models
Hojjat Aghakhani, Wei Dai, Andre Manoel +7
With tools like GitHub Copilot, automatic code suggestion is no longer a dream in software engineering. These tools, based on large language models, are typically trained on massiv…
Combing for Credentials: Active Pattern Extraction from Smart Reply
Bargav Jayaraman, Esha Ghosh, Melissa Chase +3
Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the…
EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation
Roshan Dathathri, Blagovesta Kostova, Olli Saarikivi +3
Fully-Homomorphic Encryption (FHE) offers powerful capabilities by enabling secure offloading of both storage and computation, and recent innovations in schemes and implementations…
HEAX: An Architecture for Computing on Encrypted Data
M. Sadegh Riazi, Kim Laine, Blake Pelton +1
With the rapid increase in cloud computing, concerns surrounding data privacy, security, and confidentiality also have been increased significantly. Not only cloud providers are su…
Commutative-like Encryption: A New Characterization of ElGamal
Wei Dai
Commutative encryption is a useful but rather strict notion in cryptography. In this paper, we deny a loose variation of commutative encryption-commutative-like encryption and give…