activity
20062024
most citedHow To Break Anonymity of the Netflix Prize Dataset

270 citations · 444 across the 14 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.CL2020★ 1 cited

Adversarial Semantic Collisions

Congzheng Song, Alexander M. Rush, Vitaly Shmatikov

We study semantic collisions: texts that are semantically unrelated but judged as similar by NLP models. We develop gradient-based approaches for generating semantic collisions and…

cs.CR2020

You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion

Roei Schuster, Congzheng Song, Eran Tromer +1

Code autocompletion is an integral feature of modern code editors and IDEs. The latest generation of autocompleters uses neural language models, trained on public open-source code…

cs.CR2020

De-Anonymizing Text by Fingerprinting Language Generation

Zhen Sun, Roei Schuster, Vitaly Shmatikov

Components of machine learning systems are not (yet) perceived as security hotspots. Secure coding practices, such as ensuring that no execution paths depend on confidential inputs…

cs.CR2020

Blind Backdoors in Deep Learning Models

Eugene Bagdasaryan, Vitaly Shmatikov

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstr…

cs.LG2020

Salvaging Federated Learning by Local Adaptation

Tao Yu, Eugene Bagdasaryan, Vitaly Shmatikov

Federated learning (FL) is a heavily promoted approach for training ML models on sensitive data, e.g., text typed by users on their smartphones. FL is expressly designed for traini…

cs.CL2020

Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning

Roei Schuster, Tal Schuster, Yoav Meri +1

Word embeddings, i.e., low-dimensional vector representations such as GloVe and SGNS, encode word "meaning" in the sense that distances between words' vectors correspond to their s…