Manan Sanghi

Hamsa: fast signature generation for zero-day polymorphic worms with provable attack resilience

Zero-day polymorphic worms pose a serious threat to the security of Internet infrastructures. Given their rapid propagation, it is crucial to detect them at edge networks and automatically generate signatures in the early stages of infection. Most existing approaches for automatic signature generation need host information and are thus not applicable for deployment on high-speed network links. In this paper, we propose Hamsa, a network-based automated signature generation system for polymorphic worms which is fast, noise-tolerant and attack-resilient. Essentially, we propose a realistic model to analyze the invariant content of polymorphic worms which allows us to make analytical attack-resilience guarantees for the signature generation algorithm. Evaluation based on a range of polymorphic worms and polymorphic engines demonstrates that Hamsa significantly outperforms Polygraph (J. Newsome et al., 2005) in terms of efficiency, accuracy, and attack resilience

Fast algorithms for finding matchings in lopsided bipartite graphs with applications to display ads

We derive efficient algorithms for both detecting and representing matchings in lopsided bipartite graphs; such graphs have so many nodes on one side that it is infeasible to represent them in memory or to identify matchings using standard approaches. Detecting and representing matchings in lopsided bipartite graphs is important for allocating and delivering guaranteed-placement display ads, where the corresponding bipartite graph of interest has nodes representing advertisers on one side and nodes representing web-page impressions on the other; real-world instances of such graphs can have billions of impression nodes. We provide theoretical guarantees for our algorithms, and in a real-world advertising application, we demonstrate the feasibility of our detection algorithms.

An optimization problem in adaptive virtual environments

A virtual execution environment consisting of virtual machines (VMs) interconnected with virtual networks provides opportunities to dynamically optimize, at run-time, the performance of existing, unmodified distributed applications without any user or programmer intervention. Along with resource monitoring and inference and application-independent adaptation mechanisms, efficient adaptation algorithms are key to the success of such an effort. In previous work we have described our measurement and inference framework, explained our adaptation mechanisms, and proposed simple heuristics as adaptation algorithms. Though we were successful in improving performance as compared to the case with no adaptation, none of our algorithms were characterized by theoretically proven bounds. In this paper, we formalize the adaptation problem, show that it is NP-hard and propose research directions for coming up with an efficient solution.

Hardness of Approximation and Greedy Algorithms for the Adaptation Problem in Virtual Environments

Over the past decade, wide-area distributed computing has emerged as a powerful computing paradigm. Virtual machines greatly simplify wide-area distributed computing by lowering the abstraction to benefit both resource users and providers. A virtual execution environment consisting of virtual machines (VMs) interconnected with virtual networks provides opportunities to dynamically optimize, at run-time, the performance of existing, unmodified distributed applications without any user or programmer intervention. We have formalized the adaptation problem in virtual execution environments and shown that it is NP-hard to both, solve and approximate within a factor of m1/2-δfor any δ > 0, where m is the number of edges in the virtual overlay graph. We also designed and evaluated greedy adaptation algorithms and found them to work well in practice.

Randomized fast design of short DNA words

We consider the problem of efficiently designing sets (codes) of equal-length DNA strings (words) that satisfy certain combinatorial constraints. This problem has numerous motivations including DNA computing and DNA self-assembly. Previous work has extended results from coding theory to obtain bounds on code size for new biologically motivated constraints and has applied heuristic local search and genetic algorithm techniques for code design. This paper proposes a natural optimization formulation of the DNA code design problem in which the goal is to design n strings that satisfy a given set of constraints while minimizing the length of the strings. For multiple sets of constraints, we provide high-probability algorithms that run in time polynomial in n and any given constraint parameters, and output strings of length within a constant factor of the optimal. To the best of our knowledge, this work is the first to consider this type of optimization problem in the context of DNA code design.

Flexible word design and graph labeling

Motivated by emerging applications for DNA code word design, we consider a generalization of the code word design problem in which an input graph is given which must be labeled with equal length binary strings of minimal length such that the Hamming distance is small between words of adjacent nodes and large between words of non-adjacent nodes. For general graphs we provide algorithms that bound the word length with respect to either the maximum degree of any vertex or the number of edges in either the input graph or its complement. We further provide multiple types of recursive, deterministic algorithms for trees and forests, and provide an improvement for forests that makes use of randomization.

An approximation algorithm for a bottleneck traveling salesman problem

Consider a truck running along a road. It picks up a load Li at point βi and delivers it at αi, carrying at most one load at a time. The speed on the various parts of the road in one direction is given by f(x) and that in the other direction is given by g(x). Minimizing the total time spent to deliver loads L1,...,Ln is equivalent to solving the Traveling Salesman Problem (TSP) where the cities correspond to the loads Li with coordinates (αi, βi) and the distance from Li to Lj is given by

POLYPHONIC MUSICAL SEQUENCE ALIGNMENT FOR DATABASE SEARCH

\int^{\beta_j}_{\alpha_i} f(x)dx

LINEAR-PROGRAM FORMULATION FOR OPTIMIZING INVENTORY ALLOCATION

if βj ≥ αi and by

ADVERTISING INVENTORY PREDICTION FOR FREQUENCY-CAPPED LINES

\int^{\alpha_i}_{\beta_j} g(x)dx