SPLASH 2020
Sun 15 - Sat 21 November 2020 Online Conference
Wed 18 Nov 2020 13:00 - 13:20 at SPLASH-I - W-4 Chair(s): Justin Hsu, Eric Koskinen
Thu 19 Nov 2020 01:00 - 01:20 at SPLASH-I - W-4 Chair(s): Sophia Drossopoulou, Jan Vitek

Neural models of code have shown impressive results when performing tasks such as predicting method names and identifying certain kinds of bugs.
We show that these models are vulnerable to \emph{adversarial examples}, and introduce a novel approach for \emph{attacking} trained models of code using adversarial examples.
The main idea of our approach is to force a given trained model to make an incorrect prediction, as specified by the adversary, by introducing small perturbations that do not change the program's semantics, thereby creating an adversarial example.
To find such perturbations, we present a new technique for Discrete Adversarial Manipulation of Programs (DAMP). DAMP works by deriving the desired prediction with respect to the model's \emph{inputs}, while holding the model weights constant, and following the gradients to slightly modify the input code.

We show that our DAMP attack is effective across three neural architectures: code2vec, GGNN, and GNN-FiLM, in both Java and C#.
Our evaluations demonstrate that DAMP has up to 89% success rate in changing a prediction to the adversary's choice (a targeted attack) and a success rate of up to 94% in changing a given prediction to any incorrect prediction (a non-targeted attack).
To defend a model against such attacks, we empirically examine a variety of possible defenses and discuss their trade-offs.
We show that some of these defenses can dramatically drop the success rate of the attacker, with a minor penalty of 2% relative degradation in accuracy when they are not performing under attack.

Our code, data, and trained models are available at \url{https://github.com/tech-srl/adversarial-examples} .

Conference Day
Wed 18 Nov

Displayed time zone: Central Time (US & Canada) change

13:00 - 14:20
W-4OOPSLA at SPLASH-I +12h
Chair(s): Justin HsuUniversity of Wisconsin-Madison, USA, Eric KoskinenStevens Institute of Technology
13:00
20m
Talk
Adversarial Examples for Models of Code
OOPSLA
Noam YefetTechnion, Uri AlonTechnion, Eran YahavTechnion
Link to publication DOI Pre-print Media Attached
13:20
20m
Talk
Finding Bugs in Database Systems via Query Partitioning
OOPSLA
Manuel RiggerETH Zurich, Zhendong SuETH Zurich
Link to publication DOI Pre-print Media Attached
13:40
20m
Talk
Proving Highly-Concurrent Traversals Correct
OOPSLA
Yotam M. Y. FeldmanTel Aviv University, Artem KhyzhaTel Aviv University, Constantin EneaUniversity of Paris / IRIF / CNRS, Adam MorrisonTel Aviv University, Aleksandar NanevskiIMDEA Software Institute, Noam RinetzkyTel Aviv University, Sharon ShohamTel Aviv University
Link to publication DOI Media Attached
14:00
20m
Talk
How Do Programmers Use Unsafe Rust?
OOPSLA
Vytautas AstrauskasETH Zurich, Christoph MathejaETH Zurich, Federico PoliETH Zurich, Peter MüllerETH Zurich, Alexander J. SummersUniversity of British Columbia
Link to publication DOI Media Attached

Conference Day
Thu 19 Nov

Displayed time zone: Central Time (US & Canada) change

01:00 - 02:20
W-4OOPSLA at SPLASH-I
Chair(s): Sophia DrossopoulouImperial College London, Jan VitekNortheastern University / Czech Technical University
01:00
20m
Talk
Adversarial Examples for Models of Code
OOPSLA
Noam YefetTechnion, Uri AlonTechnion, Eran YahavTechnion
Link to publication DOI Pre-print Media Attached
01:20
20m
Talk
Finding Bugs in Database Systems via Query Partitioning
OOPSLA
Manuel RiggerETH Zurich, Zhendong SuETH Zurich
Link to publication DOI Pre-print Media Attached
01:40
20m
Talk
Proving Highly-Concurrent Traversals Correct
OOPSLA
Yotam M. Y. FeldmanTel Aviv University, Artem KhyzhaTel Aviv University, Constantin EneaUniversity of Paris / IRIF / CNRS, Adam MorrisonTel Aviv University, Aleksandar NanevskiIMDEA Software Institute, Noam RinetzkyTel Aviv University, Sharon ShohamTel Aviv University
Link to publication DOI Media Attached
02:00
20m
Talk
How Do Programmers Use Unsafe Rust?
OOPSLA
Vytautas AstrauskasETH Zurich, Christoph MathejaETH Zurich, Federico PoliETH Zurich, Peter MüllerETH Zurich, Alexander J. SummersUniversity of British Columbia
Link to publication DOI Media Attached