V
Vitaly Shmatikov
Researcher at Cornell University
Publications - 153
Citations - 22828
Vitaly Shmatikov is an academic researcher from Cornell University. The author has contributed to research in topics: Anonymity & Information privacy. The author has an hindex of 64, co-authored 148 publications receiving 17801 citations. Previous affiliations of Vitaly Shmatikov include University of Texas at Austin & French Institute for Research in Computer Science and Automation.
Papers
More filters
Proceedings ArticleDOI
Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning
TL;DR: In this paper, the authors demonstrate that an attacker who can modify the corpus on which the embedding is trained can control the meaning of new and existing words by changing their locations in the embeddings space.
Proceedings ArticleDOI
Adversarial Semantic Collisions
TL;DR: The authors develop gradient-based approaches for generating semantic collisions and demonstrate that state-of-the-art models for many tasks including paraphrase identification, document retrieval, response suggestion, and extractive summarization are vulnerable to semantic collisions.
Proceedings ArticleDOI
Towards computationally sound symbolic analysis of key exchange protocols
Prateek Gupta,Vitaly Shmatikov +1 more
TL;DR: In this paper, the authors present a cryptographically sound formal method for proving correctness of key exchange protocols using a fragment of a symbolic protocol logic, and demonstrate that proofs of key agreement and key secrecy in this logic imply simulatability in Shoup's secure multi-party framework for key exchange.
Posted Content
Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning
TL;DR: This work develops an explicit expression over corpus features that serves as a proxy for distance between words and establishes a causative relationship between its values and embedding distances, and shows how the attacker can generate linguistically likely corpus modifications, thus fooling defenses that attempt to filter implausible sentences from the corpus using a language model.
Proceedings ArticleDOI
Rethinking Security of Web-Based System Applications
TL;DR: PowerGate enables application developers to write well-defined native-object access policies with explicit principals such as "application's own local code and "third-party Web code," is easy to configure, and incurs negligible performance overhead.