• Publications
  • Influence
Towards the Science of Security and Privacy in Machine Learning
TLDR
It is shown that there are (possibly unavoidable) tensions between model complexity, accuracy, and resilience that must be calibrated for the environments in which they will be used, and formally explores the opposing relationship between model accuracy and resilience to adversarial manipulation.
SoK: Security and Privacy in Machine Learning
TLDR
It is apparent that constructing a theoretical understanding of the sensitivity of modern ML algorithms to the data they analyze, à la PAC theory, will foster a science of security and privacy in ML.
Stackelberg Security Games: Looking Beyond a Decade of Success
TLDR
A broad survey of recent technical advances in Stackelberg Security Game and related literature is presented, and the future is highlighted by highlighting the new potential applications and open research problems in SSG.
CAPTURE: A New Predictive Anti-Poaching Tool for Wildlife Protection
TLDR
This paper presents the largest dataset of real-world defender-adversary interactions analyzed in the security games literature, and presents a new predictive anti-poaching tool, CAPTURE, which provides significant advances over previous models from behavioral game theory and conservation biology.
One Size Does Not Fit All: A Game-Theoretic Approach for Dynamically and Effectively Screening for Threats
TLDR
This work proposes a threat screening game (TSG) model for general screening domains, an NP-hardness proof for computing the optimal strategy of TSGs, and a novel algorithm that exploits a compact game representation to efficiently solve TSGs.
Provable De-anonymization of Large Datasets with Sparse Dimensions
TLDR
A variant of the Narayanan-Shmatikov algorithm that was used to effectively de-anonymize the Netflix database of movie ratings is analyzed and it is proved that theorems characterizing mathematical properties of the database and the auxiliary information available to the adversary that enable two classes of privacy attacks are proved.
Understanding and Protecting Privacy: Formal Semantics and Principled Audit Mechanisms
TLDR
A semantic model and logic of privacy is described that formalizes privacy as a right to appropriate flows of personal information—a position taken by contextual integrity, a philosphical theory of privacy for answering questions of the form identified in (a).
Program Actions as Actual Causes: A Building Block for Accountability
TLDR
This work defines in an interacting program model what it means for a set of program actions to be an actual cause of a violation, and provides a cause analysis of a representative protocol designed to address weaknesses in the current public key certification infrastructure.
From physical security to cybersecurity
TLDR
Cast the problem as a Stackelberg game, new algorithms are developed that are now deployed over multiple years in multiple applications for scheduling of security resources and highlight the innovations in security games that could be used to tackle the game problem in cybersecurity.
Continuous Tamper-Proof Logging Using TPM 2.0
TLDR
An infrastructure for secure logging that is capable of detecting the tampering of logs by powerful adversaries residing on the device where logs are generated and relies on novel features of trusted hardware TPM to ensure the continuity of the logging infrastructure across power cycles without help from a remote server is presented.
...
1
2
3
4
5
...