arXiv subjects

Osbert Bastani

Publications and source records attributed to Osbert Bastani.

122 records · Page 7Linked to original sources

arXiv2019

Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints

In this paper, we present a learning approach to goal assignment and trajectory planning for unlabeled robots operating in 2D, obstacle-filled workspaces. More specifically, we tackle the unlabeled multi-robot motion planning problem with motion constraints as a multi-agent reinforcement learning problem with some sparse global reward. In contrast with previous works, which formulate an entirely new hand-crafted optimization cost or trajectory generation algorithm for a different robot dynamic model, our framework is a general approach that is applicable to arbitrary robot models. Further, by using the velocity obstacle, we devise a smooth projection that guarantees collision free trajectories for all robots with respect to their neighbors and obstacles. The efficacy of our algorithm is demonstrated through varied simulations.

cs.RO↗

arXiv2019

PolyDroid: Learning-Driven Specialization of Mobile Applications

The increasing prevalence of mobile apps has led to a proliferation of resource usage scenarios in which they are deployed. This motivates the need to specialize mobile apps based on diverse and varying preferences of users. We propose a system, called PolyDroid, for automatically specializing mobile apps based on user preferences. The app developer provides a number of candidate configurations, called reductions, that limit the resource usage of the original app. The key challenge underlying PolyDroid concerns learning the quality of user experience under different reductions. We propose an active learning technique that requires few user experiments to determine the optimal reduction for a given resource usage specification. On a benchmark suite comprising 20 diverse, open-source Android apps, we demonstrate that on average, PolyDroid obtains more than 85% of the optimal performance using just two user experiments.

cs.SE↗

arXiv2019

Interpreting Blackbox Models via Model Extraction

Interpretability has become incredibly important as machine learning is increasingly used to inform consequential decisions. We propose to construct global explanations of complex, blackbox models in the form of a decision tree approximating the original model---as long as the decision tree is a good approximation, then it mirrors the computation performed by the blackbox model. We devise a novel algorithm for extracting decision tree explanations that actively samples new training points to avoid overfitting. We evaluate our algorithm on a random forest to predict diabetes risk and a learned controller for cart-pole. Compared to several baselines, our decision trees are both substantially more accurate and equally or more interpretable based on a user study. Finally, we describe several insights provided by our interpretations, including a causal issue validated by a physician.

cs.LG↗

arXiv2019

Verifiable Reinforcement Learning via Policy Extraction

While deep reinforcement learning has successfully solved many challenging control tasks, its real-world applicability has been limited by the inability to ensure the safety of learned policies. We propose an approach to verifiable reinforcement learning by training decision tree policies, which can represent complex policies (since they are nonparametric), yet can be efficiently verified using existing techniques (since they are highly structured). The challenge is that decision tree policies are difficult to train. We propose VIPER, an algorithm that combines ideas from model compression and imitation learning to learn decision tree policies guided by a DNN policy (called the oracle) and its Q-function, and show that it substantially outperforms two baselines. We use VIPER to (i) learn a provably robust decision tree policy for a variant of Atari Pong with a symbolic state space, (ii) learn a decision tree policy for a toy game based on Pong that provably never loses, and (iii) learn a provably stable decision tree policy for cart-pole. In each case, the decision tree policy achieves performance equal to that of the original DNN policy.

cs.LG↗

arXiv2019

Learning Neurosymbolic Generative Models via Program Synthesis

Significant strides have been made toward designing better generative models in recent years. Despite this progress, however, state-of-the-art approaches are still largely unable to capture complex global structure in data. For example, images of buildings typically contain spatial patterns such as windows repeating at regular intervals; state-of-the-art generative methods can't easily reproduce these structures. We propose to address this problem by incorporating programs representing global structure into the generative model---e.g., a 2D for-loop may represent a configuration of windows. Furthermore, we propose a framework for learning these models by leveraging program synthesis to generate training data. On both synthetic and real-world data, we demonstrate that our approach is substantially better than the state-of-the-art at both generating and completing images that contain global structure.

cs.LG↗

arXiv2018

Active Learning of Points-To Specifications

When analyzing programs, large libraries pose significant challenges to static points-to analysis. A popular solution is to have a human analyst provide points-to specifications that summarize relevant behaviors of library code, which can substantially improve precision and handle missing code such as native code. We propose ATLAS, a tool that automatically infers points-to specifications. ATLAS synthesizes unit tests that exercise the library code, and then infers points-to specifications based on observations from these executions. ATLAS automatically infers specifications for the Java standard library, and produces better results for a client static information flow analysis on a benchmark of 46 Android apps compared to using existing handwritten specifications.

cs.PL↗

arXiv2018

Interpretability via Model Extraction

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox models. Our approach approximates the complex model using a much more interpretable model; as long as the approximation quality is good, then statistical properties of the complex model are reflected in the interpretable model. We show how model extraction can be used to understand and debug random forests and neural nets trained on several datasets from the UCI Machine Learning Repository, as well as control policies learned for several classical reinforcement learning problems.

cs.LG↗

arXiv2017

Program Synthesis using Conflict-Driven Learning

We propose a new conflict-driven program synthesis technique that is capable of learning from past mistakes. Given a spurious program that violates the desired specification, our synthesis algorithm identifies the root cause of the conflict and learns new lemmas that can prevent similar mistakes in the future. Specifically, we introduce the notion of equivalence modulo conflict and show how this idea can be used to learn useful lemmas that allow the synthesizer to prune large parts of the search space. We have implemented a general-purpose CDCL-style program synthesizer called Neo and evaluate it in two different application domains, namely data wrangling in R and functional programming over lists. Our experiments demonstrate the substantial benefits of conflict-driven learning and show that Neo outperforms two state-of-the-art synthesis tools, Morpheus and Deepcoder, that target these respective domains.

cs.PL↗

arXiv2017

Eventually Sound Points-To Analysis with Missing Code

Static analyses make the increasingly tenuous assumption that all source code is available for analysis; for example, large libraries often call into native code that cannot be analyzed. We propose a points-to analysis that initially makes optimistic assumptions about missing code, and then inserts runtime checks that report counterexamples to these assumptions that occur during execution. Our approach guarantees eventual soundness, i.e., the static analysis is sound for the available code after some finite number of counterexamples. We implement Optix, an eventually sound points-to analysis for Android apps, where the Android framework is missing. We show that the runtime checks added by Optix incur low overhead on real programs, and demonstrate how Optix improves a client information flow analysis for detecting Android malware.

cs.PL↗

arXiv2017

Measuring Neural Net Robustness with Constraints

Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled. We propose metrics for measuring the robustness of a neural net and devise a novel algorithm for approximating these metrics based on an encoding of robustness as a linear program. We show how our metrics can be used to evaluate the robustness of deep neural nets with experiments on the MNIST and CIFAR-10 datasets. Our algorithm generates more informative estimates of robustness metrics compared to estimates based on existing algorithms. Furthermore, we show how existing approaches to improving robustness "overfit" to adversarial examples generated using a specific algorithm. Finally, we show that our techniques can be used to additionally improve neural net robustness both according to the metrics that we propose, but also according to previously proposed metrics.

cs.LG↗

arXiv2017

Synthesizing Program Input Grammars

We present an algorithm for synthesizing a context-free grammar encoding the language of valid program inputs from a set of input examples and blackbox access to the program. Our algorithm addresses shortcomings of existing grammar inference algorithms, which both severely overgeneralize and are prohibitively slow. Our implementation, GLADE, leverages the grammar synthesized by our algorithm to fuzz test programs with structured inputs. We show that GLADE substantially increases the incremental coverage on valid inputs compared to two baseline fuzzers.

cs.PL↗

arXiv2017

Automated Synthesis of Semantic Malware Signatures using Maximum Satisfiability

This paper proposes a technique for automatically learning semantic malware signatures for Android from very few samples of a malware family. The key idea underlying our technique is to look for a maximally suspicious common subgraph (MSCS) that is shared between all known instances of a malware family. An MSCS describes the shared functionality between multiple Android applications in terms of inter-component call relations and their semantic metadata (e.g., data-flow properties). Our approach identifies such maximally suspicious common subgraphs by reducing the problem to maximum satisfiability. Once a semantic signature is learned, our approach uses a combination of static analysis and a new approximate signature matching algorithm to determine whether an Android application matches the semantic signature characterizing a given malware family. We have implemented our approach in a tool called ASTROID and show that it has a number of advantages over state-of-the-art malware detection techniques. First, we compare the semantic malware signatures automatically synthesized by ASTROID with manually-written signatures used in previous work and show that the signatures learned by ASTROID perform better in terms of accuracy as well as precision. Second, we compare ASTROID against two state-of-the-art malware detection tools and demonstrate its advantages in terms of interpretability and accuracy. Finally, we demonstrate that ASTROID's approximate signature matching algorithm is resistant to behavioral obfuscation and that it can be used to detect zero-day malware. In particular, we were able to find 22 instances of zero-day malware in Google Play that are not reported as malware by existing tools.

cs.CR↗

arXiv2013

Zero-Shot Learning Through Cross-Modal Transfer

This work introduces a model that can recognize objects in images even if no training data is available for the objects. The only necessary knowledge about the unseen categories comes from unsupervised large text corpora. In our zero-shot framework distributional information in language can be seen as spanning a semantic basis for understanding what objects look like. Most previous zero-shot learning models can only differentiate between unseen classes. In contrast, our model can both obtain state of the art performance on classes that have thousands of training images and obtain reasonable performance on unseen classes. This is achieved by first using outlier detection in the semantic space and then two separate recognition models. Furthermore, our model does not require any manually defined semantic features for either words or images.

cs.CV↗

arXiv2011

Randomization, Sums of Squares, and Faster Real Root Counting for Tetranomials and Beyond

Suppose f is a real univariate polynomial of degree D with exactly 4 monomial terms. We present an algorithm, with complexity polynomial in log D on average (relative to the stable log-uniform measure), for counting the number of real roots of f. The best previous algorithms had complexity super-linear in D. We also discuss connections to sums of squares and A-discriminants, including explicit obstructions to expressing positive definite sparse polynomials as sums of squares of few sparse polynomials. Our key tool is the introduction of efficiently computable chamber cones, bounding regions in coefficient space where the number of real roots of f can be computed easily. Much of our theory extends to n-variate (n+3)-nomials.

math.AG↗