• Publications
  • Influence
PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
TLDR
Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. Expand
Learning to Automatically Solve Algebra Word Problems
TLDR
We present an approach for automatically learning to solve algebra word problems, demonstrating that the system can correctly answer almost 70% of the questions in the dataset. Expand
Learning to Solve Arithmetic Word Problems with Verb Categorization
TLDR
This paper presents a novel approach to learning to solve simple arithmetic word problems by mapping the verbs in the problem text into categories that describe their impact on the world state. Expand
R-BGP: Staying Connected in a Connected World
TLDR
R-BGP provably guarantees that a domain will not become disconnected from any destination as long as it will have a policy compliant path to that destination. Expand
ZipTx: Harnessing Partial Packets in 802.11 Networks
TLDR
We introduce ZipTx, a software-only solution that harvests the gains from using correct bits in corrupted packets using existing hardware, and evaluate our implementation in both outdoor and indoor environments, showing that ZipTx significantly improves the throughput. Expand
Constructing Unrestricted Adversarial Examples with Generative Models
TLDR
We propose unrestricted adversarial examples, a new threat model where the attackers are not restricted to small norm-bounded perturbations. Expand
Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
TLDR
This paper explores the task of translating natural language queries into regular expressions which embody their meaning. Expand
Learning to share: narrowband-friendly wideband networks
TLDR
This paper presents SWIFT, the first system where high-throughput wideband nodes are shown in a working deployment to coexist with unknown narrowband devices, while forming a network of their own. Expand
Using Semantic Unification to Generate Regular Expressions from Natural Language
TLDR
We consider the problem of translating natural language text queries into regular expressions which represent their meaning. Expand
Can you hear me now?!: it must be BGP
TLDR
This paper investigates the factors that prevent cross-domain VoIP deployments from achieving the quality and reliability of existing land-line telephony (PSTN). Expand
...
1
2
3
4
...